diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7587f71bffc..694c1f53c31 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -40,6 +40,7 @@ "vector_store_cost_per_gb_per_day": 0.0 }, "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { + "deprecation_date": "2026-09-30", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -52,12 +53,6 @@ "mode": "image_generation", "output_cost_per_image": 0.04 }, - "1024-x-1024/dall-e-2": { - "input_cost_per_pixel": 1.9e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -65,12 +60,6 @@ "mode": "image_generation", "output_cost_per_image": 0.08 }, - "256-x-256/dall-e-2": { - "input_cost_per_pixel": 2.4414e-07, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -78,12 +67,6 @@ "mode": "image_generation", "output_cost_per_image": 0.018 }, - "512-x-512/dall-e-2": { - "input_cost_per_pixel": 6.86e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -98,7 +81,8 @@ "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 1.25e-05 + "output_cost_per_token": 1.25e-05, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.j2-ultra-v1": { "input_cost_per_token": 1.88e-05, @@ -107,25 +91,30 @@ "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 1.88e-05 + "output_cost_per_token": 1.88e-05, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-1-5-large-v1:0": { + "deprecation_date": "2026-11-26", "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 8e-06 + "output_cost_per_token": 8e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-1-5-mini-v1:0": { + "deprecation_date": "2026-11-26", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 4e-07 + "output_cost_per_token": 4e-07, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "ai21.jamba-instruct-v1:0": { "input_cost_per_token": 5e-07, @@ -135,6 +124,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_system_messages": true }, "aiml/dall-e-2": { @@ -287,6 +277,7 @@ "supports_vision": true }, "amazon.nova-canvas-v1:0": { + "deprecation_date": "2026-09-30", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -294,6 +285,7 @@ "supports_nova_canvas_image_edit": true }, "us.amazon.nova-canvas-v1:0": { + "deprecation_date": "2026-09-30", "litellm_provider": "bedrock", "max_input_tokens": 2600, "mode": "image_generation", @@ -308,6 +300,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true }, @@ -319,6 +312,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true }, @@ -330,6 +324,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true }, @@ -341,10 +336,23 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -356,7 +364,8 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -372,25 +381,28 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_image_token": 1.25e-06, + "input_cost_per_audio_token": 1.25e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, @@ -408,25 +420,28 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "apac.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, @@ -444,25 +459,28 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "eu.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, @@ -480,25 +498,28 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "us.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, @@ -520,6 +541,7 @@ "supports_audio_input": true }, "amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -529,9 +551,11 @@ "output_cost_per_token": 1.4e-07, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_tool_choice": true }, "amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -543,7 +567,18 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true + }, + "amazon.nova-2-sonic-v1:0": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "bedrock", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2.75e-06, + "supports_audio_input": true, + "supports_audio_output": true }, "amazon.rerank-v1:0": { "input_cost_per_query": 0.001, @@ -620,7 +655,11 @@ "mode": "image_generation" }, "twelvelabs.marengo-embed-2-7-v1:0": { - "input_cost_per_token": 7e-05, + "deprecation_date": "2026-11-30", + "input_cost_per_query": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, "max_tokens": 77, @@ -631,7 +670,8 @@ "supports_image_input": true }, "us.twelvelabs.marengo-embed-2-7-v1:0": { - "input_cost_per_token": 7e-05, + "deprecation_date": "2026-11-30", + "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, @@ -645,7 +685,8 @@ "supports_image_input": true }, "eu.twelvelabs.marengo-embed-2-7-v1:0": { - "input_cost_per_token": 7e-05, + "deprecation_date": "2026-11-30", + "input_cost_per_query": 7e-05, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, @@ -658,6 +699,48 @@ "supports_embedding_image_input": true, "supports_image_input": true }, + "twelvelabs.marengo-embed-3-0-v1:0": { + "input_cost_per_query": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "litellm_provider": "bedrock", + "max_input_tokens": 500, + "max_tokens": 500, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 512, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "us.twelvelabs.marengo-embed-3-0-v1:0": { + "input_cost_per_query": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "litellm_provider": "bedrock", + "max_input_tokens": 500, + "max_tokens": 500, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 512, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "eu.twelvelabs.marengo-embed-3-0-v1:0": { + "input_cost_per_query": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "litellm_provider": "bedrock", + "max_input_tokens": 500, + "max_tokens": 500, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 512, + "supports_embedding_image_input": true, + "supports_image_input": true + }, "twelvelabs.pegasus-1-2-v1:0": { "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, @@ -679,6 +762,14 @@ "mode": "chat", "supports_video_input": true }, + "global.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "amazon.titan-text-express-v1": { "input_cost_per_token": 1.3e-06, "litellm_provider": "bedrock", @@ -730,12 +821,13 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -747,7 +839,9 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5e-07, + "output_cost_per_token_batches": 2.5e-06 }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -755,6 +849,7 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -858,22 +953,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -889,22 +968,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", @@ -918,6 +981,7 @@ "anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2027-01-08", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, @@ -973,6 +1037,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -996,15 +1061,18 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1029,15 +1097,18 @@ "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1062,15 +1133,18 @@ "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1095,15 +1169,18 @@ "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1128,15 +1205,18 @@ "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.875e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1161,7 +1241,8 @@ "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1171,6 +1252,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1192,27 +1274,33 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-mythos-preview": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "cache_creation_input_token_cost": 3.4375e-05, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.75e-05, + "output_cost_per_token": 0.0001375, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_output_config": true + "supports_output_config": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1222,6 +1310,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1243,12 +1332,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1258,6 +1348,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1279,12 +1370,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1294,6 +1386,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1315,12 +1408,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1330,6 +1424,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1351,12 +1446,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1375,6 +1471,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -1392,7 +1489,47 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1411,6 +1548,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -1428,7 +1566,47 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1447,6 +1625,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -1464,7 +1643,47 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "us.anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.375e-05, @@ -1483,6 +1702,7 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -1500,7 +1720,514 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "eu.anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512 + }, + "anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "global.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "us.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "us.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "eu.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "eu.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "au.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "au.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "jp.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.75e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "jp.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1511,6 +2238,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1532,12 +2260,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1548,6 +2277,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1569,12 +2299,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1585,6 +2316,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1606,12 +2338,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1622,6 +2355,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1643,12 +2377,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1659,6 +2394,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1680,12 +2416,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -1696,6 +2433,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1717,19 +2455,22 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1752,11 +2493,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1765,6 +2507,7 @@ "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1788,12 +2531,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1802,6 +2546,7 @@ "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1825,12 +2570,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1839,6 +2585,7 @@ "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1862,12 +2609,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1876,6 +2624,7 @@ "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1899,12 +2648,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1913,6 +2663,7 @@ "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1936,12 +2687,13 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -1950,6 +2702,7 @@ "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -1973,20 +2726,23 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2010,15 +2766,18 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2042,15 +2801,18 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2074,15 +2836,18 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2106,15 +2871,18 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2138,15 +2906,18 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_1hr": 6.6e-06, "cache_read_input_token_cost": 3.3e-07, "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2170,11 +2941,13 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-14", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -2201,7 +2974,8 @@ "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -2214,6 +2988,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2235,7 +3010,10 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -2375,6 +3153,7 @@ "supports_function_calling": true }, "apac.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.575e-08, "input_cost_per_token": 6.3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -2386,9 +3165,11 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "apac.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 9.25e-09, "input_cost_per_token": 3.7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -2398,9 +3179,11 @@ "output_cost_per_token": 1.48e-07, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_tool_choice": true }, "apac.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.1e-07, "input_cost_per_token": 8.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -2412,64 +3195,15 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true - }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 + "supports_tool_choice": true }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2487,27 +3221,14 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 - }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-07, + "output_cost_per_token_batches": 2.75e-06 }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-14", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -2534,7 +3255,8 @@ "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -2559,6 +3281,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -2580,18 +3303,24 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.65e-06, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "azure/ada": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, + "deprecation_date": "2026-11-15", "input_cost_per_token": 1.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -2599,6 +3328,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -2620,6 +3350,7 @@ "supports_vision": true }, "azure/command-r-plus": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 128000, @@ -2627,9 +3358,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true }, "azure_ai/claude-haiku-4-5": { + "deprecation_date": "2026-11-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, @@ -2648,9 +3381,12 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-5": { + "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, @@ -2670,14 +3406,18 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { + "deprecation_date": "2027-02-02", "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -2699,14 +3439,16 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 4096 }, "azure_ai/claude-opus-4-7": { + "deprecation_date": "2027-04-06", "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -2729,9 +3471,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 2048 }, "azure_ai/claude-fable-5": { + "deprecation_date": "2027-12-05", + "supports_mid_conversation_system": true, "input_cost_per_token": 1e-05, "output_cost_per_token": 5e-05, "litellm_provider": "azure_ai", @@ -2748,6 +3493,7 @@ "cache_creation_input_token_cost_above_1hr": 2e-05, "cache_read_input_token_cost": 1e-06, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -2759,14 +3505,53 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 }, - "azure_ai/claude-opus-4-8": { + "azure_ai/claude-fable-5-1": { + "supports_mid_conversation_system": true, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-12-05" + }, + "azure_ai/claude-opus-5": { + "deprecation_date": "2027-07-08", + "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "input_cost_per_token": 5e-06, "output_cost_per_token": 2.5e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -2789,30 +3574,79 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 }, - "azure_ai/claude-opus-4-1": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, + "azure_ai/claude-opus-5-5": { + "supports_mid_conversation_system": true, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 + }, + "azure_ai/claude-opus-4-8": { + "deprecation_date": "2027-09-01", + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { + "deprecation_date": "2026-11-30", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, @@ -2831,9 +3665,13 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { + "deprecation_date": "2027-06-30", + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, @@ -2861,18 +3699,21 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-6": { + "deprecation_date": "2027-02-10", "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -2885,7 +3726,9 @@ "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, "azure/computer-use-preview": { "input_cost_per_token": 3e-06, @@ -2895,6 +3738,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -2927,13 +3771,210 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, + "azure_ai/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://ai.azure.com/catalog/models/gpt-6-astra", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure_ai/gpt-5.5": { + "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -2943,7 +3984,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -2979,6 +4020,95 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure_ai/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-10-21", + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true + }, + "azure_ai/codex-mini": { + "cache_read_input_token_cost": 3.75e-07, + "deprecation_date": "2026-11-15", + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/whisper": { + "deprecation_date": "2026-12-15", + "input_cost_per_second": 0.0001, + "litellm_provider": "azure_ai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" + }, "azure_ai/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, @@ -2989,7 +4119,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -3025,7 +4155,55 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-5.4": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -3035,7 +4213,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -3068,10 +4246,12 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-2026-03-05": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, @@ -3081,7 +4261,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -3114,10 +4294,12 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -3127,7 +4309,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -3163,6 +4345,7 @@ "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-pro-2026-03-05": { + "deprecation_date": "2027-09-07", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "cache_read_input_token_cost_priority": 6e-06, @@ -3172,7 +4355,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -3208,23 +4391,18 @@ "supports_minimal_reasoning_effort": true }, "azure_ai/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1.5e-07, "cache_read_input_token_cost_priority": 1.5e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07, "input_cost_per_token": 7.5e-07, - "input_cost_per_token_above_272k_tokens": 1.5e-06, "input_cost_per_token_priority": 1.5e-06, - "input_cost_per_token_above_272k_tokens_priority": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, - "output_cost_per_token_above_272k_tokens": 6.75e-06, "output_cost_per_token_priority": 9e-06, - "output_cost_per_token_above_272k_tokens_priority": 1.35e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", @@ -3250,27 +4428,23 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4-mini-2026-03-17": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1.5e-07, "cache_read_input_token_cost_priority": 1.5e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07, "input_cost_per_token": 7.5e-07, - "input_cost_per_token_above_272k_tokens": 1.5e-06, "input_cost_per_token_priority": 1.5e-06, - "input_cost_per_token_above_272k_tokens_priority": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, - "output_cost_per_token_above_272k_tokens": 6.75e-06, "output_cost_per_token_priority": 9e-06, - "output_cost_per_token_above_272k_tokens_priority": 1.35e-05, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", @@ -3296,27 +4470,23 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_priority": 4e-08, - "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_priority": 4e-07, - "input_cost_per_token_above_272k_tokens_priority": 8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, - "output_cost_per_token_above_272k_tokens": 1.875e-06, "output_cost_per_token_priority": 2.5e-06, - "output_cost_per_token_above_272k_tokens_priority": 3.75e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", @@ -3342,27 +4512,23 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/gpt-5.4-nano-2026-03-17": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_priority": 4e-08, - "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, "input_cost_per_token_priority": 4e-07, - "input_cost_per_token_above_272k_tokens_priority": 8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 400000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, - "output_cost_per_token_above_272k_tokens": 1.875e-06, "output_cost_per_token_priority": 2.5e-06, - "output_cost_per_token_above_272k_tokens_priority": 3.75e-06, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", @@ -3388,27 +4554,47 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "azure_ai/model_router": { + "deprecation_date": "2027-05-20", "input_cost_per_token": 1.4e-07, "output_cost_per_token": 0, "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" }, + "azure_ai/model-router": { + "deprecation_date": "2027-05-20", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 0, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", + "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" + }, "azure/eu/gpt-4o-2024-08-06": { - "deprecation_date": "2026-02-27", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3417,15 +4603,19 @@ "supports_vision": true }, "azure/eu/gpt-4o-2024-11-20": { - "deprecation_date": "2026-03-01", + "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -3434,13 +4624,16 @@ }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3470,6 +4663,7 @@ "azure/eu/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -3479,6 +4673,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -3492,12 +4687,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -3515,6 +4711,89 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 + }, + "azure/eu/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 + }, + "azure/eu/gpt-5.1": { + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -3531,70 +4810,6 @@ "text", "image" ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/eu/gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.75e-08, - "input_cost_per_token": 2.75e-07, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/eu/gpt-5.1": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], "supported_output_modalities": [ "text", "image" @@ -3609,51 +4824,25 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true - }, - "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3676,7 +4865,8 @@ "supports_vision": true }, "azure/eu/gpt-5.1-codex-mini": { - "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -3684,6 +4874,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3707,13 +4898,17 @@ }, "azure/eu/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, + "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3735,17 +4930,22 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3763,20 +4963,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_vision": false - }, - "azure/eu/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 8.25e-06, - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3784,6 +4971,7 @@ }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -3793,6 +4981,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -3800,14 +4989,17 @@ }, "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2026-02-27", + "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3817,14 +5009,17 @@ }, "azure/global-standard/gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2026-03-01", + "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -3832,6 +5027,7 @@ "supports_vision": true }, "azure/global-standard/gpt-4o-mini": { + "deprecation_date": "2027-04-14", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, @@ -3846,15 +5042,18 @@ "supports_vision": true }, "azure/global/gpt-4o-2024-08-06": { - "deprecation_date": "2026-02-27", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3863,15 +5062,18 @@ "supports_vision": true }, "azure/global/gpt-4o-2024-11-20": { - "deprecation_date": "2026-03-01", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -3880,7 +5082,10 @@ "supports_vision": true }, "azure/global/gpt-5.1": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -3911,43 +5116,16 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true - }, - "azure/global/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", @@ -3956,6 +5134,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3978,6 +5157,7 @@ "supports_vision": true }, "azure/global/gpt-5.1-codex-mini": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", @@ -3986,6 +5166,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4018,19 +5199,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-3.5-turbo-0125": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.5e-06, "litellm_provider": "azure_text", @@ -4050,33 +5218,8 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-35-turbo-0125": { - "deprecation_date": "2025-05-31", - "input_cost_per_token": 5e-07, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 1e-06, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, "azure/gpt-35-turbo-16k": { + "deprecation_date": "2025-04-30", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 16385, @@ -4084,9 +5227,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_tool_choice": true }, "azure/gpt-35-turbo-16k-0613": { + "deprecation_date": "2025-04-30", "input_cost_per_token": 3e-06, "litellm_provider": "azure", "max_input_tokens": 16385, @@ -4094,6 +5239,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -4114,6 +5260,7 @@ "output_cost_per_token": 2e-06 }, "azure/gpt-4": { + "deprecation_date": "2025-06-06", "input_cost_per_token": 3e-05, "litellm_provider": "azure", "max_input_tokens": 8192, @@ -4121,6 +5268,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -4137,6 +5285,7 @@ "supports_tool_choice": true }, "azure/gpt-4-0613": { + "deprecation_date": "2025-06-06", "input_cost_per_token": 3e-05, "litellm_provider": "azure", "max_input_tokens": 8192, @@ -4144,6 +5293,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -4160,6 +5310,7 @@ "supports_tool_choice": true }, "azure/gpt-4-32k": { + "deprecation_date": "2025-06-06", "input_cost_per_token": 6e-05, "litellm_provider": "azure", "max_input_tokens": 32768, @@ -4167,9 +5318,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_tool_choice": true }, "azure/gpt-4-32k-0613": { + "deprecation_date": "2025-06-06", "input_cost_per_token": 6e-05, "litellm_provider": "azure", "max_input_tokens": 32768, @@ -4177,6 +5330,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_tool_choice": true }, "azure/gpt-4-turbo": { @@ -4216,9 +5370,12 @@ "supports_vision": true }, "azure/gpt-4.1": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4226,6 +5383,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4249,10 +5408,12 @@ "supports_web_search": false }, "azure/gpt-4.1-2025-04-14": { - "deprecation_date": "2026-11-04", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4260,6 +5421,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4283,9 +5446,12 @@ "supports_web_search": false }, "azure/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4293,6 +5459,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4316,10 +5484,12 @@ "supports_web_search": false }, "azure/gpt-4.1-mini-2025-04-14": { - "deprecation_date": "2026-11-04", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4327,6 +5497,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4350,6 +5522,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -4360,6 +5533,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4382,7 +5556,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-11-04", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -4393,6 +5567,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4416,6 +5591,7 @@ }, "azure/gpt-4.5-preview": { "cache_read_input_token_cost": 3.75e-05, + "deprecation_date": "2025-07-14", "input_cost_per_token": 7.5e-05, "input_cost_per_token_batches": 3.75e-05, "litellm_provider": "azure", @@ -4425,6 +5601,7 @@ "mode": "chat", "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 7.5e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4434,6 +5611,7 @@ "supports_vision": true }, "azure/gpt-4o": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -4450,13 +5628,17 @@ "supports_vision": true }, "azure/gpt-4o-2024-05-13": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4464,15 +5646,18 @@ "supports_vision": true }, "azure/gpt-4o-2024-08-06": { - "deprecation_date": "2026-02-27", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4481,15 +5666,18 @@ "supports_vision": true }, "azure/gpt-4o-2024-11-20": { - "deprecation_date": "2026-03-01", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.75e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4497,7 +5685,41 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/gpt-audio": { + "deprecation_date": "2027-03-02", + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, "azure/gpt-audio-2025-08-28": { + "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -4528,7 +5750,8 @@ "supports_tool_choice": true, "supports_vision": false }, - "azure/gpt-audio-1.5-2026-02-23": { + "azure/gpt-audio-1.5": { + "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -4557,9 +5780,75 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": false, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, + "azure/gpt-audio-1.5-2026-02-23": { + "deprecation_date": "2027-08-24", + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-audio-mini": { + "deprecation_date": "2027-06-15", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_vision": false }, "azure/gpt-audio-mini-2025-10-06": { + "deprecation_date": "2027-04-06", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "azure", @@ -4622,14 +5911,15 @@ "supports_vision": false }, "azure/gpt-4o-mini": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4639,13 +5929,17 @@ }, "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.65e-07, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4703,11 +5997,48 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-06, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-03-02", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, "azure/gpt-realtime-2025-08-28": { "cache_creation_input_audio_token_cost": 4e-06, - "cache_read_input_token_cost": 4e-06, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -4735,11 +6066,13 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "azure/gpt-realtime-1.5-2026-02-23": { + "azure/gpt-realtime-1.5": { "cache_creation_input_audio_token_cost": 4e-06, - "cache_read_input_token_cost": 4e-06, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -4765,13 +6098,154 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + }, + "azure/gpt-realtime-1.5-2026-02-23": { + "cache_creation_input_audio_token_cost": 4e-06, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-08-24", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1-mini": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-mini": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-15", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, "azure/gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-04-06", "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -4800,7 +6274,8 @@ "supports_tool_choice": true }, "azure/gpt-4o-mini-transcribe": { - "input_cost_per_audio_token": 1.25e-06, + "deprecation_date": "2027-06-15", + "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -4812,7 +6287,8 @@ ] }, "azure/gpt-4o-mini-tts": { - "input_cost_per_token": 2.5e-06, + "deprecation_date": "2027-06-15", + "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, @@ -4832,6 +6308,7 @@ "azure/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2e-05, "cache_read_input_token_cost": 2.5e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -4841,6 +6318,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -4853,12 +6331,13 @@ "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -4875,6 +6354,7 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { + "deprecation_date": "2026-10-15", "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -4882,11 +6362,13 @@ "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { + "deprecation_date": "2027-04-15", "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -4899,10 +6381,14 @@ ] }, "azure/gpt-realtime-whisper": { + "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "audio_transcription", - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -4918,6 +6404,7 @@ "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-05-15", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", @@ -4950,47 +6437,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "azure/gpt-5.1-chat-2025-11-13": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": true + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-05-15", "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", @@ -5000,6 +6457,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5024,6 +6482,7 @@ "azure/gpt-5.1-codex-mini-2025-11-13": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-05-15", "input_cost_per_token": 2.5e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", @@ -5033,6 +6492,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5055,14 +6515,22 @@ "supports_vision": true }, "azure/gpt-5": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5088,13 +6556,20 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2027-02-09", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5116,75 +6591,12 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2027-03-17", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -5192,6 +6604,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5214,14 +6627,22 @@ "supports_vision": true }, "azure/gpt-5-mini": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5247,13 +6668,20 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-02-09", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5275,17 +6703,23 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_batches": 2.5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5311,13 +6745,17 @@ }, "azure/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, + "deprecation_date": "2027-02-09", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5339,17 +6777,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { + "deprecation_date": "2027-04-07", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "output_cost_per_token_batches": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5371,7 +6813,10 @@ "supports_vision": true }, "azure/gpt-5.1": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -5402,20 +6847,27 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-5.1-chat": { + "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-06-29", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -5423,22 +6875,237 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" + ], + "supports_prompt_caching": true, + "supports_vision": true + }, + "azure/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" ], "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true + "supports_tool_choice": true + }, + "azure/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/us/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.375e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/us/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/us/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.375e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "max_input_tokens": 111616, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure/us/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2025-07-28", + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_prompt_caching": true + }, + "azure/eu/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2025-07-28", + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_prompt_caching": true }, "azure/gpt-5.1-codex": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", @@ -5447,6 +7114,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5470,6 +7138,7 @@ }, "azure/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2027-05-18", "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -5477,6 +7146,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5499,6 +7169,7 @@ "supports_vision": true }, "azure/gpt-5.1-codex-mini": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "azure", @@ -5507,6 +7178,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5529,14 +7201,22 @@ "supports_vision": true }, "azure/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_batches": 8.75e-08, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5564,7 +7244,9 @@ "azure/gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, "cache_read_input_token_cost_priority": 3.5e-07, + "deprecation_date": "2027-06-08", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -5572,7 +7254,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5595,78 +7279,12 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5.2-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/gpt-5.2-chat-2025-12-11": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2027-07-13", "input_cost_per_token": 1.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -5674,6 +7292,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5695,49 +7314,20 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.3-chat": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "deprecation_date": "2027-08-24", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5761,12 +7351,20 @@ }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -5792,12 +7390,20 @@ }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -5822,16 +7428,20 @@ "supports_web_search": true }, "azure/gpt-5.4": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_read_input_token_cost_batches": 1.3e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -5860,17 +7470,34 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { - "cache_read_input_token_cost": 2.8e-07, + "deprecation_date": "2027-09-02", + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -5895,17 +7522,32 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { - "cache_read_input_token_cost": 2.8e-07, + "deprecation_date": "2027-09-02", + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -5930,19 +7572,32 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "deprecation_date": "2027-09-02", "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -5971,17 +7626,34 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, + "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -6006,17 +7678,32 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, + "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -6041,20 +7728,48 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_batches": 0.000135, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6081,15 +7796,28 @@ "azure/gpt-5.4-pro-2026-03-05": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "deprecation_date": "2027-09-07", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6111,26 +7839,37 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6159,23 +7898,106 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6204,23 +8026,106 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-terra": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost_priority": 5e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "input_cost_per_token_priority": 5e-06, - "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "output_cost_per_token_priority": 3e-05, - "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6249,23 +8154,42 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-luna": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_priority": 2e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "input_cost_per_token_priority": 2e-06, - "input_cost_per_token_above_272k_tokens_priority": 4e-06, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "output_cost_per_token_priority": 1.2e-05, - "output_cost_per_token_above_272k_tokens_priority": 1.8e-05, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6293,21 +8217,563 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, - "azure/us/gpt-5.6": { - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-luna-2026-09-22": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-sol-2026-09-22": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/chat-latest": { + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/gpt-5.6": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6336,20 +8802,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6378,20 +8858,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-terra": { - "cache_read_input_token_cost": 2.75e-07, - "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, - "cache_read_input_token_cost_priority": 6.875e-07, - "input_cost_per_token": 2.75e-06, - "input_cost_per_token_above_272k_tokens": 5.5e-06, - "input_cost_per_token_priority": 6.875e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_above_272k_tokens": 2.475e-05, - "output_cost_per_token_priority": 4.125e-05, + "output_cost_per_token": 1.32e-05, + "output_cost_per_token_above_272k_tokens": 1.98e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, + "output_cost_per_token_priority": 2.64e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6420,20 +8914,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-luna": { - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, - "cache_read_input_token_cost_priority": 2.75e-07, - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_above_272k_tokens": 2.2e-06, - "input_cost_per_token_priority": 2.75e-06, + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, + "cache_creation_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, + "cache_read_input_token_cost_priority": 4.4e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_above_272k_tokens": 4.4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "output_cost_per_token_above_272k_tokens": 9.9e-06, - "output_cost_per_token_priority": 1.65e-05, + "output_cost_per_token": 1.32e-06, + "output_cost_per_token_above_272k_tokens": 1.98e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, + "output_cost_per_token_priority": 2.64e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6461,21 +8969,217 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, - "azure/eu/gpt-5.6": { - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "azure/us/gpt-6-astra": { + "deprecation_date": "2028-01-11", + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-6-luna": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, + "cache_read_input_token_cost": 1.1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_above_272k_tokens": 2.2e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "output_cost_per_token_above_272k_tokens": 8.25e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-6-sol": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-chat-latest": { + "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/eu/gpt-5.6": { + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6504,20 +9208,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6546,20 +9264,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-terra": { - "cache_read_input_token_cost": 2.75e-07, - "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, - "cache_read_input_token_cost_priority": 6.875e-07, - "input_cost_per_token": 2.75e-06, - "input_cost_per_token_above_272k_tokens": 5.5e-06, - "input_cost_per_token_priority": 6.875e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_above_272k_tokens": 2.475e-05, - "output_cost_per_token_priority": 4.125e-05, + "output_cost_per_token": 1.32e-05, + "output_cost_per_token_above_272k_tokens": 1.98e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-05, + "output_cost_per_token_priority": 2.64e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6588,20 +9320,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-luna": { - "cache_read_input_token_cost": 1.1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, - "cache_read_input_token_cost_priority": 2.75e-07, - "input_cost_per_token": 1.1e-06, - "input_cost_per_token_above_272k_tokens": 2.2e-06, - "input_cost_per_token_priority": 2.75e-06, + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06, + "cache_creation_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08, + "cache_read_input_token_cost_priority": 4.4e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_above_272k_tokens": 4.4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "output_cost_per_token_above_272k_tokens": 9.9e-06, - "output_cost_per_token_priority": 1.65e-05, + "output_cost_per_token": 1.32e-06, + "output_cost_per_token_above_272k_tokens": 1.98e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.96e-06, + "output_cost_per_token_priority": 2.64e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6630,23 +9376,39 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.5": { + "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_batches": 2.5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token_batches": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6675,20 +9437,33 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.5": { + "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, + "output_cost_per_token_batches": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6717,20 +9492,33 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.5": { + "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, + "output_cost_per_token_batches": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6761,21 +9549,29 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_batches": 2.5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6798,12 +9594,83 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_flex": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 7.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -6811,10 +9678,15 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6837,12 +9709,75 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -6850,10 +9785,15 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6876,7 +9816,68 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -6890,6 +9891,11 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6929,6 +9935,11 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6953,14 +9964,23 @@ "supports_web_search": true }, "azure/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6984,18 +10004,34 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7019,18 +10055,35 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_batches": 1e-08, + "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7054,18 +10107,31 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-07, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7089,11 +10155,19 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -7123,6 +10197,7 @@ "output_cost_per_token": 0.0 }, "azure/high/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -7132,6 +10207,7 @@ ] }, "azure/high/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -7141,6 +10217,7 @@ ] }, "azure/high/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "azure", "mode": "image_generation", @@ -7150,6 +10227,7 @@ ] }, "azure/low/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7159,6 +10237,7 @@ ] }, "azure/low/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7168,6 +10247,7 @@ ] }, "azure/low/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7177,6 +10257,7 @@ ] }, "azure/medium/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7186,6 +10267,7 @@ ] }, "azure/medium/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7195,6 +10277,7 @@ ] }, "azure/medium/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7205,6 +10288,7 @@ }, "azure/gpt-image-1-mini": { "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-04-07", "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -7216,6 +10300,7 @@ ] }, "azure/gpt-image-1.5": { + "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -7229,6 +10314,7 @@ }, "azure/gpt-image-1.5-2025-12-16": { "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", @@ -7240,12 +10326,42 @@ ] }, "azure/gpt-image-2": { + "deprecation_date": "2027-10-21", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-flare": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-sunburst": { + "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -7256,11 +10372,11 @@ }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-10-21", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 1e-05, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -7270,6 +10386,7 @@ "supports_pdf_input": true }, "azure/low/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7279,6 +10396,7 @@ ] }, "azure/low/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 2.0751953125e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7288,6 +10406,7 @@ ] }, "azure/low/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 2.0345052083e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7297,6 +10416,7 @@ ] }, "azure/medium/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7306,6 +10426,7 @@ ] }, "azure/medium/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 8.056640625e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7315,6 +10436,7 @@ ] }, "azure/medium/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 7.9752604167e-09, "litellm_provider": "azure", "mode": "image_generation", @@ -7324,6 +10446,7 @@ ] }, "azure/high/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7333,6 +10456,7 @@ ] }, "azure/high/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 3.173828125e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7342,6 +10466,7 @@ ] }, "azure/high/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2027-04-07", "input_cost_per_pixel": 3.1575520833e-08, "litellm_provider": "azure", "mode": "image_generation", @@ -7369,6 +10494,7 @@ "supports_function_calling": true }, "azure/o1": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", @@ -7386,13 +10512,17 @@ }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -7401,14 +10531,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.84e-06, + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -7418,50 +10551,23 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, - "azure/o1-preview": { - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": false - }, - "azure/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": false - }, "azure/o3": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -7491,15 +10597,18 @@ "supports_vision": true }, "azure/o3-2025-04-16": { - "deprecation_date": "2026-04-16", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7522,6 +10631,7 @@ }, "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -7529,6 +10639,12 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7553,6 +10669,7 @@ "supports_web_search": true }, "azure/o3-mini": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -7569,19 +10686,24 @@ }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/o3-pro": { + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -7591,6 +10713,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7612,6 +10735,7 @@ "supports_vision": true }, "azure/o3-pro-2025-06-10": { + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -7621,6 +10745,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7642,6 +10767,7 @@ "supports_vision": true }, "azure/o4-mini": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -7672,13 +10798,17 @@ }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -7712,29 +10842,34 @@ "output_cost_per_token": 0.0 }, "azure/text-embedding-3-large": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" }, "azure/text-embedding-3-small": { - "deprecation_date": "2026-04-30", + "deprecation_date": "2028-02-09", "input_cost_per_token": 2e-08, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" }, "azure/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -7760,20 +10895,24 @@ ] }, "azure/tts-1": { + "deprecation_date": "2026-12-15", "input_cost_per_character": 1.5e-05, "litellm_provider": "azure", "mode": "audio_speech" }, "azure/tts-1-hd": { + "deprecation_date": "2026-12-15", "input_cost_per_character": 3e-05, "litellm_provider": "azure", "mode": "audio_speech" }, "azure/us/gpt-4.1-2025-04-14": { - "deprecation_date": "2026-11-04", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -7781,6 +10920,8 @@ "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7804,10 +10945,12 @@ "supports_web_search": false }, "azure/us/gpt-4.1-mini-2025-04-14": { - "deprecation_date": "2026-11-04", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -7815,6 +10958,8 @@ "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7838,10 +10983,10 @@ "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-11-04", - "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -7849,6 +10994,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7871,15 +11017,18 @@ "supports_vision": true }, "azure/us/gpt-4o-2024-08-06": { - "deprecation_date": "2026-02-27", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -7888,15 +11037,19 @@ "supports_vision": true }, "azure/us/gpt-4o-2024-11-20": { - "deprecation_date": "2026-03-01", + "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -7905,13 +11058,16 @@ }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -7941,6 +11097,7 @@ "azure/us/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -7950,6 +11107,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -7963,12 +11121,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -7986,6 +11145,126 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 + }, + "azure/us/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 + }, + "azure/us/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5.5e-09, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 + }, + "azure/us/gpt-5.1": { + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8002,102 +11281,6 @@ "text", "image" ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/us/gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.75e-08, - "input_cost_per_token": 2.75e-07, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/us/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5.5e-09, - "input_cost_per_token": 5.5e-08, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 4.4e-07, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/us/gpt-5.1": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], "supported_output_modalities": [ "text", "image" @@ -8112,51 +11295,25 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true - }, - "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-05, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -8179,7 +11336,8 @@ "supports_vision": true }, "azure/us/gpt-5.1-codex-mini": { - "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8187,6 +11345,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -8210,13 +11369,17 @@ }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8234,35 +11397,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_vision": false - }, - "azure/us/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 8.25e-06, - "input_cost_per_token": 1.65e-05, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false }, "azure/us/o3-2025-04-16": { - "deprecation_date": "2026-04-16", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8285,6 +11438,7 @@ }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -8294,20 +11448,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-07, + "cache_read_input_token_cost": 3.03e-07, + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -8317,6 +11476,7 @@ "supports_vision": true }, "azure/whisper-1": { + "deprecation_date": "2026-12-15", "input_cost_per_second": 0.0001, "litellm_provider": "azure", "mode": "audio_transcription", @@ -8330,7 +11490,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, "azure_ai/Cohere-embed-v3-multilingual": { @@ -8341,11 +11501,33 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true }, + "azure_ai/Codestral-2501": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_native_streaming": true + }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -8355,106 +11537,427 @@ }, "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/flux.2-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/images/generations" ] }, + "azure_ai/FLUX.2-flex": { + "input_cost_per_pixel": 5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "image_generation", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "azure_ai/FW-DeepSeek-V3.2": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 3.1e-07, + "input_cost_per_token": 6.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1.85e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.65e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.828e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.52e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5.1": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 2.86e-07, + "input_cost_per_token": 1.54e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5.2": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.54e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.31e-07, + "input_cost_per_token": 2.31e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.26e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-Inkling": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.46e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-Kimi-K2.5": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.3e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/FW-Kimi-K2.6": { + "cache_read_input_token_cost": 1.76e-07, + "input_cost_per_token": 1.045e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/FW-Kimi-K2.7-Code": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 1.05e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/FW-Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/FW-MiniMax-M2.5": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 3.3e-08, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-MiniMax-M3": { + "cache_read_input_token_cost": 6.6e-08, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.64e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/MAI-Image-2.5": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.05, + "output_cost_per_image": 0.048, "output_cost_per_image_token": 4.7e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" - ] + ], + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { "input_cost_per_image_token": 1.75e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.0338, - "output_cost_per_image_token": 3.3e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "output_cost_per_image": 0.02, + "output_cost_per_image_token": 1.95e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 + }, + "azure_ai/MAI-Image-2.5-Pro": { + "deprecation_date": "2026-10-01", + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "mode": "image_generation", + "output_cost_per_image": 0.1085, + "output_cost_per_image_token": 0.000106, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-mai-image-2-5-pro-and-mai-voice-2-flash-in-microsoft-foundry/4539446", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, - "azure_ai/MAI-Image-2e": { - "input_cost_per_token": 5e-06, + "azure_ai/MAI-Thinking-1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "output_cost_per_image_token": 1.95e-05, - "source": "https://aka.ms/mai-image-2e-foundryblog", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "input_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-07, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "input_cost_per_token": 2.04e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.04e-06, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, "azure_ai/Llama-3.3-70B-Instruct": { "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 1.41e-06, + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 1e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -8473,6 +11976,7 @@ "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -8480,20 +11984,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.7e-07, - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "input_cost_per_token": 5.33e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 1.6e-05, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8501,21 +11996,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.54e-06, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "input_cost_per_token": 3e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.1e-07, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Phi-3-medium-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8523,11 +12008,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-medium-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -8535,11 +12021,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8547,11 +12034,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -8559,11 +12047,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8571,11 +12060,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-8k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -8583,11 +12073,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-MoE-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8595,11 +12086,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-mini-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8607,11 +12099,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-vision-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8619,7 +12112,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": true }, @@ -8631,7 +12124,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -8644,7 +12137,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -8656,20 +12149,20 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -8680,20 +12173,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true }, - "azure_ai/mistral-document-ai-2505": { - "litellm_provider": "azure_ai", - "ocr_cost_per_page": 0.003, - "mode": "ocr", - "supported_endpoints": [ - "/v1/ocr" - ], - "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" - }, "azure_ai/mistral-document-ai-2512": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.003, @@ -8701,7 +12185,39 @@ "supported_endpoints": [ "/v1/ocr" ], - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/" + "source": "https://ai.azure.com/catalog/models/mistral-document-ai-2512" + }, + "azure_ai/mistral-ocr-4-0": { + "litellm_provider": "azure_ai", + "ocr_cost_per_page": 0.004, + "annotation_cost_per_page": 0.005, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/" + }, + "azure_ai/Cohere-parse-v5": { + "deprecation_date": "2026-12-15", + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.0015, + "source": "https://cohere.com/blog/parse", + "supported_endpoints": [ + "/v1/ocr" + ] + }, + "azure_ai/cohere-command-a": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8182, + "max_tokens": 8182, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_tool_choice": true }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", @@ -8731,6 +12247,7 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8738,11 +12255,12 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/cohere-rerank-v3-english": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -8750,9 +12268,11 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v3-multilingual": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -8760,17 +12280,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 - }, - "azure_ai/cohere-rerank-v3.5": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v4.0-pro": { "input_cost_per_query": 0.0025, @@ -8797,12 +12308,12 @@ "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -8812,31 +12323,20 @@ "azure_ai/deepseek-v3.2-speciale": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, - "azure_ai/deepseek-r1": { - "input_cost_per_token": 1.35e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5.4e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v3": { + "deprecation_date": "2025-08-31", "input_cost_per_token": 1.14e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -8844,35 +12344,11 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3-0324": { - "input_cost_per_token": 1.14e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3.1": { - "input_cost_per_token": 1.23e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.94e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", - "supports_function_calling": true, - "supports_reasoning": true, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/deepseek-v4-pro": { + "deprecation_date": "2028-02-20", "input_cost_per_token": 1.74e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, @@ -8880,12 +12356,15 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.45e-07, + "supports_prompt_caching": true }, "azure_ai/deepseek-v4-flash": { + "deprecation_date": "2028-02-20", "input_cost_per_token": 1.9e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, @@ -8893,9 +12372,27 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, + "supports_tool_choice": true, + "cache_read_input_token_cost": 2.8e-08, + "supports_prompt_caching": true + }, + "azure_ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 1.4e-08, + "deprecation_date": "2026-12-03", + "input_cost_per_token": 4.4e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { @@ -8906,7 +12403,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -8914,116 +12411,111 @@ "text", "image" ], - "supports_embedding_image_input": true - }, - "azure_ai/global/grok-3": { - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/global/grok-3-mini": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3": { - "input_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3-mini": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.27e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, - "azure_ai/grok-4-fast-non-reasoning": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, + "azure_ai/grok-4.3": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true }, - "azure_ai/grok-4-fast-reasoning": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 5e-07, + "azure_ai/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure_ai/grok-4-20-reasoning": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-04-06", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 262000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_reasoning": true + }, + "azure_ai/grok-4-20-non-reasoning": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2027-04-06", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 262000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true }, "azure_ai/grok-4-1-fast-non-reasoning": { "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -9033,11 +12525,11 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -9047,18 +12539,19 @@ "azure_ai/grok-code-fast-1": { "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 0.0032, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -9066,9 +12559,10 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, - "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/jamba-instruct": { + "deprecation_date": "2025-03-01", "input_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 70000, @@ -9076,9 +12570,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/kimi-k2.5": { + "deprecation_date": "2027-01-26", "input_cost_per_token": 6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, @@ -9086,13 +12582,16 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true }, "azure_ai/kimi-k2.6": { + "deprecation_date": "2027-04-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, @@ -9100,7 +12599,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -9111,7 +12610,9 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.6e-07, + "supports_prompt_caching": true }, "azure_ai/ministral-3b": { "input_cost_per_token": 4e-08, @@ -9121,11 +12622,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-large": { + "deprecation_date": "2025-04-15", "input_cost_per_token": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -9133,10 +12635,12 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-large-2407": { + "deprecation_date": "2025-05-13", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -9144,7 +12648,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -9156,7 +12660,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_function_calling": true, "supports_tool_choice": true }, @@ -9168,7 +12672,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -9186,6 +12690,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-nemo": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -9193,10 +12698,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true }, "azure_ai/mistral-small": { + "deprecation_date": "2025-07-31", "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -9204,6 +12710,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -9220,110 +12727,129 @@ "supports_vision": true }, "babbage-002": { + "deprecation_date": "2026-09-28", "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", - "output_cost_per_token": 4e-07 + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.001902, "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.001902, "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.0011416, "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.0066027, "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, + "bedrock/guardrails": { + "guardrail_cost_per_unit": { + "automatedReasoningPolicyUnits": 0.00017, + "contentPolicyImageUnits": 0.00075, + "contentPolicyUnits": 0.00015, + "contextualGroundingPolicyUnits": 0.0001, + "sensitiveInformationPolicyFreeUnits": 0.0, + "sensitiveInformationPolicyUnits": 0.0001, + "topicPolicyUnits": 0.00015, + "wordPolicyUnits": 0.0 + }, + "litellm_provider": "bedrock", + "mode": "guardrail", + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01475, "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01475, "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0455 + "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0455, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.008194, "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.008194, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02527 + "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02527, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { @@ -9366,7 +12892,11 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { @@ -9380,6 +12910,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { @@ -9394,6 +12927,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { @@ -9419,6 +12955,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { @@ -9432,6 +12970,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/moonshotai.kimi-k2-thinking": { @@ -9459,7 +13000,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 3.18e-06, @@ -9489,7 +13032,11 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { @@ -9503,6 +13050,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { @@ -9517,6 +13067,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { @@ -9542,6 +13095,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { @@ -9555,21 +13110,27 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { - "input_cost_per_token": 3.09e-07, + "input_cost_per_token": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "output_cost_per_token": 1.236e-06 + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, + "output_cost_per_token": 1.24e-06 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, @@ -9581,7 +13142,11 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { @@ -9595,6 +13160,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { @@ -9609,6 +13177,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { @@ -9623,6 +13194,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { @@ -9636,6 +13209,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { @@ -9666,7 +13242,11 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { @@ -9680,6 +13260,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { @@ -9694,6 +13277,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { @@ -9708,64 +13294,66 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01635, "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01635, "supports_tool_choice": true }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0415 + "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0415, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.009083, "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.009083, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02305 + "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02305, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { @@ -9808,6 +13396,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { @@ -9822,6 +13413,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { @@ -9835,6 +13429,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { @@ -9866,6 +13463,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { @@ -9880,6 +13480,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { @@ -9893,6 +13496,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { @@ -9924,6 +13530,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { @@ -9938,8 +13547,28 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.86e-06 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.01e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "litellm_provider": "bedrock", @@ -9951,6 +13580,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { @@ -9964,13 +13596,14 @@ "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 1.04e-05, + "input_cost_per_token": 5.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 3.12e-05, + "output_cost_per_token": 1.56e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { @@ -9994,6 +13627,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/eu-south-1/minimax.minimax-m2.5": { @@ -10008,6 +13644,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { @@ -10021,6 +13660,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { @@ -10069,7 +13711,11 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { @@ -10083,6 +13729,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { @@ -10097,6 +13746,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.44e-06 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { @@ -10122,6 +13774,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { @@ -10135,64 +13789,67 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-instant-v1": { @@ -10254,13 +13911,14 @@ "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 1.2e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { @@ -10283,7 +13941,11 @@ "output_cost_per_token": 1.85e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/minimax.minimax-m2.1": { @@ -10297,6 +13959,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/minimax.minimax-m2.5": { @@ -10310,6 +13975,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { @@ -10335,6 +14003,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { @@ -10348,6 +14018,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-2/deepseek.v3.2": { @@ -10360,7 +14033,11 @@ "output_cost_per_token": 1.85e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-2/minimax.minimax-m2.1": { @@ -10374,6 +14051,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-2/minimax.minimax-m2.5": { @@ -10388,6 +14068,9 @@ "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "output_cost_per_token": 1.2e-06 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { @@ -10413,6 +14096,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { @@ -10426,9 +14111,13 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 300000, @@ -10440,7 +14129,8 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { "input_cost_per_token": 1e-07, @@ -10487,44 +14177,13 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, @@ -10549,6 +14208,7 @@ "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, @@ -10587,7 +14247,54 @@ "output_cost_per_token": 2.65e-06, "supports_pdf_input": true }, + "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 8172, + "max_tokens": 8172, + "mode": "embedding", + "input_cost_per_token": 1.62e-07, + "input_cost_per_image": 7.2e-05, + "input_cost_per_video_per_second": 0.00084, + "input_cost_per_audio_per_second": 0.000168, + "output_cost_per_token": 0.0, + "output_vector_size": 3072, + "supports_embedding_image_input": true, + "supports_image_input": true, + "supports_video_input": true, + "supports_audio_input": true + }, + "bedrock/us-gov-west-1/amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.8e-08, + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_tool_choice": true + }, + "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 1.05e-08, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.68e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.4e-07, "input_cost_per_token": 9.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 300000, @@ -10599,7 +14306,8 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { "input_cost_per_token": 1e-07, @@ -10646,64 +14354,13 @@ "mode": "chat", "output_cost_per_token": 1.5e-06 }, - "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 4.5e-06, - "cache_read_input_token_cost": 3.6e-07, - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "input_cost_per_token": 3.6e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-07, - "cache_creation_input_token_cost": 4.5e-06 - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 3e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3.75e-07 - }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, "cache_creation_input_token_cost_above_1hr": 7.2e-06, "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, @@ -10728,6 +14385,7 @@ "cache_read_input_token_cost": 3.6e-07, "input_cost_per_token": 3.6e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, @@ -10763,7 +14421,7 @@ "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 2.65e-06, + "output_cost_per_token": 6e-07, "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { @@ -10785,61 +14443,61 @@ "output_cost_per_token": 6e-07 }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-instant-v1": { @@ -10883,13 +14541,14 @@ "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 1.2e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { @@ -10912,7 +14571,11 @@ "output_cost_per_token": 1.85e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/minimax.minimax-m2.1": { @@ -10926,6 +14589,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/minimax.minimax-m2.5": { @@ -10939,6 +14605,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { @@ -10964,6 +14633,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_audio_input": false, + "supports_response_schema": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { @@ -10977,6 +14648,9 @@ "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { @@ -11132,32 +14806,21 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "cerebras/zai-glm-4.6": { - "deprecation_date": "2026-01-20", - "input_cost_per_token": 2.25e-06, + "cerebras/qwen-3.8-27b": { + "input_cost_per_token": 9.9e-07, "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", + "output_cost_per_token": 1.49e-06, + "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true - }, - "cerebras/zai-glm-4.7": { - "input_cost_per_token": 2.25e-06, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-06, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "chatdolphin": { "input_cost_per_token": 5e-07, @@ -11168,22 +14831,6 @@ "mode": "chat", "output_cost_per_token": 5e-07 }, - "chatgpt-4o-latest": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe-diarize": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -11194,21 +14841,29 @@ "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" - ] + ], + "deprecation_date": "2027-02-26", + "input_cost_per_second": 0.0001, + "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -11221,16 +14876,21 @@ "claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -11238,129 +14898,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 - }, - "claude-3-7-sonnet-20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-02-19", - "input_cost_per_token": 3e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "claude-3-haiku-20240307": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-3-opus-20240229": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 1.5e-06, - "deprecation_date": "2026-05-01", - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-4-opus-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-4-sonnet-20250514": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, @@ -11371,13 +14910,22 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11393,7 +14941,8 @@ "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, @@ -11404,13 +14953,22 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11427,28 +14985,80 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -11462,30 +15072,41 @@ "us": 1.1 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/models/sonnet-5-5/overview", + "supports_web_search": true }, "claude-sonnet-4-6": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11493,7 +15114,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "provider_specific_entry": { + "us": 1.1 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -11506,6 +15131,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -11521,104 +15147,25 @@ "supports_tool_choice": true, "supports_vision": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-1": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-1-20250805": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-08-05", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "deprecation_date": "2026-05-14", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_batches": 7.5e-06 }, "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11629,6 +15176,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11640,14 +15188,18 @@ "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11658,80 +15210,95 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "provider_specific_entry": { - "us": 1.1, - "fast": 6.0 + "us": 1.1 }, "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_speed": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6-20260205": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "provider_specific_entry": { - "us": 1.1, - "fast": 6.0 + "us": 1.1 }, "supports_max_reasoning_effort": true, "supports_output_config": true, @@ -11739,16 +15306,21 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11760,6 +15332,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11769,24 +15342,29 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { - "us": 1.1, - "fast": 6.0 + "us": 1.1 }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-7-20260416": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11798,6 +15376,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11807,30 +15386,36 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { - "us": 1.1, - "fast": 6.0 + "us": 1.1 }, "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -11847,30 +15432,131 @@ "us": 1.1 }, "supports_output_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-opus-4-8": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "claude-fable-5-1": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "claude-opus-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2.0 + }, + "supports_output_config": true, + "supports_speed": true, + "supports_fast_mode": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "claude-opus-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11885,39 +15571,88 @@ }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 1024 + "supports_fast_mode": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-sonnet-4-20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "claude-opus-4-8": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1, + "fast": 2.0 + }, + "supports_output_config": true, + "supports_speed": true, + "supports_fast_mode": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + }, + "cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + }, + "cloudflare/@cf/cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + }, + "cloudflare/@cf/cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, @@ -11926,7 +15661,8 @@ "max_output_tokens": 3072, "max_tokens": 3072, "mode": "chat", - "output_cost_per_token": 1.923e-06 + "output_cost_per_token": 1.923e-06, + "rpm": 300 }, "cloudflare/@cf/meta/llama-2-7b-chat-int8": { "input_cost_per_token": 1.923e-06, @@ -11935,7 +15671,8 @@ "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 1.923e-06 + "output_cost_per_token": 1.923e-06, + "rpm": 300 }, "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { "input_cost_per_token": 1.923e-06, @@ -11944,7 +15681,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.923e-06 + "output_cost_per_token": 1.923e-06, + "rpm": 300 }, "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { "input_cost_per_token": 1.923e-06, @@ -11953,7 +15691,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.923e-06 + "output_cost_per_token": 1.923e-06, + "rpm": 300 }, "cloudflare/@cf/openai/gpt-oss-120b": { "input_cost_per_token": 3.5e-07, @@ -11963,6 +15702,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -11973,7 +15713,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "rpm": 300 }, "cloudflare/@cf/meta/llama-3.2-3b-instruct": { "input_cost_per_token": 5.09e-08, @@ -11982,7 +15723,8 @@ "max_output_tokens": 80000, "max_tokens": 80000, "mode": "chat", - "output_cost_per_token": 3.35e-07 + "output_cost_per_token": 3.35e-07, + "rpm": 300 }, "cloudflare/@cf/meta/llama-guard-3-8b": { "input_cost_per_token": 4.84e-07, @@ -11991,7 +15733,8 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-08 + "output_cost_per_token": 3e-08, + "rpm": 300 }, "cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": { "input_cost_per_token": 0.0, @@ -12000,7 +15743,8 @@ "max_output_tokens": 15000, "max_tokens": 15000, "mode": "chat", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "rpm": 300 }, "cloudflare/@cf/moonshotai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, @@ -12011,6 +15755,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, + "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, @@ -12022,6 +15767,7 @@ "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, + "rpm": 300, "supports_reasoning": true }, "cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": { @@ -12031,7 +15777,8 @@ "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 2.87e-07 + "output_cost_per_token": 2.87e-07, + "rpm": 300 }, "cloudflare/@cf/meta/llama-3.2-1b-instruct": { "input_cost_per_token": 2.7e-08, @@ -12040,7 +15787,8 @@ "max_output_tokens": 60000, "max_tokens": 60000, "mode": "chat", - "output_cost_per_token": 2.01e-07 + "output_cost_per_token": 2.01e-07, + "rpm": 300 }, "cloudflare/@cf/moonshotai/kimi-k2.6": { "cache_read_input_token_cost": 1.6e-07, @@ -12051,6 +15799,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, + "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, @@ -12062,6 +15811,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -12072,7 +15822,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "rpm": 300 }, "cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": { "input_cost_per_token": 2.93e-07, @@ -12082,6 +15833,7 @@ "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, + "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/ibm-granite/granite-4.0-h-micro": { @@ -12092,6 +15844,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, + "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": { @@ -12101,7 +15854,8 @@ "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-06 + "output_cost_per_token": 1e-06, + "rpm": 300 }, "cloudflare/@cf/zai-org/glm-5.2": { "cache_read_input_token_cost": 2.6e-07, @@ -12112,6 +15866,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, + "rpm": 20, "supports_function_calling": true, "supports_reasoning": true }, @@ -12123,6 +15878,7 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -12133,7 +15889,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.55e-07 + "output_cost_per_token": 5.55e-07, + "rpm": 300 }, "cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": { "input_cost_per_token": 5.09e-08, @@ -12143,6 +15900,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -12153,7 +15911,8 @@ "max_output_tokens": 3500, "max_tokens": 3500, "mode": "chat", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "rpm": 300 }, "cloudflare/@cf/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1e-07, @@ -12163,6 +15922,7 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -12174,6 +15934,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, + "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": { @@ -12184,6 +15945,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, + "rpm": 300, "supports_vision": true }, "cloudflare/@cf/openai/gpt-oss-20b": { @@ -12194,6 +15956,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, + "rpm": 300, "supports_function_calling": true, "supports_reasoning": true }, @@ -12205,6 +15968,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, + "rpm": 300, "supports_function_calling": true }, "cloudflare/@cf/qwen/qwq-32b": { @@ -12215,6 +15979,7 @@ "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, + "rpm": 300, "supports_reasoning": true }, "codestral/codestral-2405": { @@ -12241,35 +16006,6 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "codex-mini-latest": { - "cache_read_input_token_cost": 3.75e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 6e-06, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "cohere.command-light-text-v14": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", @@ -12278,36 +16014,18 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_tool_choice": true - }, - "cohere.command-r-plus-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_tool_choice": true - }, - "cohere.command-r-v1:0": { - "input_cost_per_token": 5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "cohere.command-text-v14": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1e-06, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "cohere.embed-english-v3": { @@ -12317,6 +16035,7 @@ "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, "cohere.embed-multilingual-v3": { @@ -12326,6 +16045,7 @@ "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, "cohere.embed-v4:0": { @@ -12336,8 +16056,31 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_embedding_image_input": true }, + "us.cohere.embed-v4:0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536, + "supports_embedding_image_input": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.cohere.embed-v4:0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536, + "supports_embedding_image_input": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "cohere/embed-v4.0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "cohere", @@ -12346,7 +16089,40 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, - "supports_embedding_image_input": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-pro": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-fast": { + "input_cost_per_token": 8e-08, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, + "cohere/parse-v5.0": { + "litellm_provider": "cohere", + "mode": "ocr", + "ocr_cost_per_page": 0.0015, + "source": "https://cohere.com/blog/parse", + "supported_endpoints": [ + "/v1/ocr" + ] }, "cohere.rerank-v3-5:0": { "input_cost_per_query": 0.002, @@ -12358,15 +16134,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "command": { - "input_cost_per_token": 1e-06, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "completion", - "output_cost_per_token": 2e-06 - }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -12378,15 +16145,30 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-light": { - "input_cost_per_token": 3e-07, + "c4ai-aya-expanse-32b": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "cohere_chat", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_tool_choice": true + "source": "https://docs.cohere.com/docs/models" + }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "command-nightly": { "input_cost_per_token": 1e-06, @@ -12397,17 +16179,6 @@ "mode": "completion", "output_cost_per_token": 2e-06 }, - "command-r": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_tool_choice": true - }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, "litellm_provider": "cohere_chat", @@ -12419,17 +16190,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-r-plus": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true - }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, "litellm_provider": "cohere_chat", @@ -12454,8 +16214,9 @@ "supports_tool_choice": true }, "computer-use-preview": { + "deprecation_date": "2026-07-23", "input_cost_per_token": 3e-06, - "litellm_provider": "azure", + "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, @@ -12473,33 +16234,18 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true - }, - "dall-e-2": { - "input_cost_per_image": 0.02, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations", - "/v1/images/edits", - "/v1/images/variations" - ] - }, - "dall-e-3": { - "input_cost_per_image": 0.04, - "litellm_provider": "openai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] + "supports_vision": true, + "source": "https://platform.openai.com/docs/models/computer-use-preview" }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -12521,6 +16267,7 @@ }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -12541,6 +16288,103 @@ "supports_system_messages": true, "supports_tool_choice": false }, + "dashscope/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/deepseek-v4-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4.8e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 202745, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/glm-5.2": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 229376, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "dashscope/qwen-coder": { "input_cost_per_token": 3e-07, "litellm_provider": "dashscope", @@ -13284,6 +17128,113 @@ } ] }, + "dashscope/qwen3.7-max": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "dashscope/qwen3.7-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "dashscope/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", @@ -13313,7 +17264,1969 @@ "/v1/images/generations" ] }, + "dashscope/qwen-image-3.0": { + "litellm_provider": "dashscope", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "dashscope/qwen-image-3.0-pro": { + "litellm_provider": "dashscope", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwencloud/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/deepseek-v4-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4.8e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 202745, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/glm-5.2": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 229376, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwen-coder": { + "input_cost_per_token": 3e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-flash": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen-flash-2025-07-28": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen-max": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-plus": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-plus-2025-07-28": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen-plus-2025-09-11": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen-plus-latest": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen-turbo": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-turbo-latest": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwencloud", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen3-30b-a3b": { + "litellm_provider": "qwencloud", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen3-coder-flash": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3-coder-flash-2025-07-28": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3-coder-plus": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3-coder-plus-2025-07-22": { + "litellm_provider": "qwencloud", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3-max-preview": { + "litellm_provider": "qwencloud", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwencloud/qwen3-max": { + "litellm_provider": "qwencloud", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwencloud/qwen3-max-2026-01-23": { + "litellm_provider": "qwencloud", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwencloud/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "qwencloud/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwen3-vl-32b-thinking": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.87e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwen3-vl-plus": { + "litellm_provider": "qwencloud", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 4.8e-06, + "range": [ + 128000.0, + 256000.0 + ] + } + ] + }, + "qwencloud/qwen3.5-plus": { + "litellm_provider": "qwencloud", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3.7-max": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwencloud/qwen3.7-plus": { + "litellm_provider": "qwencloud", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwencloud/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "qwencloud", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwencloud/qwq-plus": { + "input_cost_per_token": 8e-07, + "litellm_provider": "qwencloud", + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://www.qwencloud.com/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwencloud/qwen-image-2.0": { + "litellm_provider": "qwencloud", + "mode": "image_generation", + "source": "https://www.qwencloud.com/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwencloud/qwen-image-2.0-pro": { + "litellm_provider": "qwencloud", + "mode": "image_generation", + "source": "https://www.qwencloud.com/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwencloud/qwen-image-3.0": { + "litellm_provider": "qwencloud", + "mode": "image_generation", + "source": "https://www.qwencloud.com/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwencloud/qwen-image-3.0-pro": { + "litellm_provider": "qwencloud", + "mode": "image_generation", + "source": "https://www.qwencloud.com/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwen_ai_platform/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/deepseek-v4-pro": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 4.8e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 202745, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/glm-5.2": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 229376, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen-coder": { + "input_cost_per_token": 3e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-flash": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen-flash-2025-07-28": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen-max": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-plus": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-plus-2025-07-28": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen-plus-2025-09-11": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen-plus-latest": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen-turbo": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-turbo-latest": { + "input_cost_per_token": 5e-08, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen3-30b-a3b": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen3-coder-flash": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-coder-flash-2025-07-28": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-coder-plus": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-coder-plus-2025-07-22": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-max-preview": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-max": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-max-2026-01-23": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen3-vl-32b-thinking": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.87e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen3-vl-plus": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 4.8e-06, + "range": [ + 128000.0, + 256000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3.5-plus": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3.7-max": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen3.7-plus": { + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "qwen_ai_platform/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "qwen_ai_platform/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "qwen_ai_platform/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "qwen_ai_platform/qwq-plus": { + "input_cost_per_token": 8e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen_ai_platform/qwen-image-2.0": { + "litellm_provider": "qwen_ai_platform", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwen_ai_platform/qwen-image-2.0-pro": { + "litellm_provider": "qwen_ai_platform", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwen_ai_platform/qwen-image-3.0": { + "litellm_provider": "qwen_ai_platform", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "qwen_ai_platform/qwen-image-3.0-pro": { + "litellm_provider": "qwen_ai_platform", + "mode": "image_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "databricks/databricks-bge-large-en": { + "cache_creation_input_token_cost": 1.0003e-07, + "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.0003e-07, "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", @@ -13328,26 +19241,68 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, - "databricks/databricks-claude-3-7-sonnet": { - "input_cost_per_token": 2.9999900000000002e-06, - "input_dbu_cost_per_token": 4.2857e-05, + "databricks/databricks-claude-fable-5": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 1.00002e-06, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, "litellm_provider": "databricks", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-claude-fable-5-1": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 2.5004e-07, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true }, "databricks/databricks-claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -13363,10 +19318,15 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 4096 }, "databricks/databricks-claude-opus-4": { + "cache_creation_input_token_cost": 1.874999e-05, + "cache_read_input_token_cost": 1.50003e-06, "input_cost_per_token": 1.5000020000000002e-05, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", @@ -13382,10 +19342,15 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-opus-4-1": { + "cache_creation_input_token_cost": 1.874999e-05, + "cache_read_input_token_cost": 1.50003e-06, "input_cost_per_token": 1.5000020000000002e-05, "input_dbu_cost_per_token": 0.000214286, "litellm_provider": "databricks", @@ -13401,10 +19366,15 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 1024 }, "databricks/databricks-claude-opus-4-5": { + "cache_creation_input_token_cost": 6.25002e-06, + "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", @@ -13420,11 +19390,160 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, - "supports_output_config": true + "supports_output_config": true, + "prompt_cache_min_tokens": 4096 + }, + "databricks/databricks-claude-opus-4-6": { + "cache_creation_input_token_cost": 6.25002e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 2.5000010000000002e-05, + "output_dbu_cost_per_token": 0.000357143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_legacy_thinking": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 4096 + }, + "databricks/databricks-claude-opus-4-7": { + "cache_creation_input_token_cost": 6.25002e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.000357143, + "prompt_cache_min_tokens": 2048, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-claude-opus-4-8": { + "cache_creation_input_token_cost": 6.25002e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.000357143, + "prompt_cache_min_tokens": 1024, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-claude-opus-5": { + "cache_creation_input_token_cost": 6.25002e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.500001e-05, + "output_dbu_cost_per_token": 0.000357143, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-claude-opus-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_creation_input_token_cost_above_1hr": 8.00002e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_output_config": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true }, "databricks/databricks-claude-sonnet-4": { + "cache_creation_input_token_cost": 3.74997e-06, + "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-10-09", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -13437,13 +19556,18 @@ "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { + "cache_creation_input_token_cost": 3.74997e-06, + "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -13459,10 +19583,14 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.74997e-06, + "cache_read_input_token_cost": 3.0002e-07, "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -13478,10 +19606,125 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 1024 + }, + "databricks/databricks-claude-sonnet-4-6": { + "cache_creation_input_token_cost": 3.74997e-06, + "cache_read_input_token_cost": 3.0002e-07, + "input_cost_per_token": 2.9999900000000002e-06, + "input_dbu_cost_per_token": 4.2857e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5000020000000002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_legacy_thinking": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_tool_choice": true, + "prompt_cache_min_tokens": 1024 + }, + "databricks/databricks-claude-sonnet-5": { + "cache_creation_input_token_cost": 3.74997e-06, + "cache_read_input_token_cost": 3.0002e-07, + "input_cost_per_token": 2.99999e-06, + "input_dbu_cost_per_token": 4.2857e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-deepseek-v4-flash-0731": { + "cache_creation_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "input_dbu_cost_per_token": 2e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." + }, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "output_dbu_cost_per_token": 4e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-deepseek-v4-pro-0813": { + "cache_creation_input_token_cost": 1.31999e-06, + "cache_read_input_token_cost": 1.3202e-07, + "input_cost_per_token": 1.31999e-06, + "input_dbu_cost_per_token": 1.8857e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." + }, + "mode": "chat", + "output_cost_per_token": 3.95997e-06, + "output_dbu_cost_per_token": 5.6571e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, "databricks/databricks-gemini-2-5-flash": { + "cache_creation_input_token_cost": 3.0002e-07, + "cache_read_input_token_cost": 3.0002e-08, + "deprecation_date": "2026-10-02", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -13496,9 +19739,26 @@ "output_dbu_cost_per_token": 3.5714e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, - "supports_tool_choice": true + "supports_anthropic_thinking_payload": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-2-5-pro": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.24999e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -13513,9 +19773,328 @@ "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, + "supports_anthropic_thinking_payload": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "deprecation_date": "2026-10-02", + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "databricks/databricks-gemini-3-1-flash-lite": { + "cache_creation_input_token_cost": 3.1248e-07, + "cache_read_input_token_cost": 3.122e-08, + "input_cost_per_token": 3.1248e-07, + "input_dbu_cost_per_token": 4.464e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.87502e-06, + "output_dbu_cost_per_token": 2.6786e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "databricks/databricks-gemini-3-1-flash-image": { + "litellm_provider": "databricks", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-pro-image": { + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-1-pro": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5000020000000002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "databricks/databricks-gemini-3-flash": { + "cache_creation_input_token_cost": 6.2503e-07, + "cache_read_input_token_cost": 6.251e-08, + "input_cost_per_token": 6.2503e-07, + "input_dbu_cost_per_token": 8.929e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 3.74997e-06, + "output_dbu_cost_per_token": 5.3571e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "databricks/databricks-gemini-3-pro": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5000020000000002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-8-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-7-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-6-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.37503e-06, + "output_dbu_cost_per_token": 0.000133929, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.124998e-05, + "output_dbu_cost_per_token": 0.000160714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash-lite": { + "cache_creation_input_token_cost": 3.7499e-07, + "cache_read_input_token_cost": 3.752e-08, + "input_cost_per_token": 3.7499e-07, + "input_dbu_cost_per_token": 5.357e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 3.12501e-06, + "output_dbu_cost_per_token": 4.4643e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "databricks/databricks-gemma-3-12b": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -13530,7 +20109,98 @@ "output_dbu_cost_per_token": 7.143e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-glm-5-2": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-glm-5-3": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-glm-5-3-flash": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 3.003e-08, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-gpt-5": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.2502e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -13543,9 +20213,14 @@ "mode": "chat", "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.2502e-07, "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -13558,9 +20233,286 @@ "mode": "chat", "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "databricks/databricks-gpt-5-2": { + "cache_creation_input_token_cost": 1.75e-06, + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "input_dbu_cost_per_token": 2.5e-05, + "litellm_provider": "databricks", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_dbu_cost_per_token": 0.0002, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "databricks/databricks-gpt-5-3-codex": { + "cache_creation_input_token_cost": 1.75e-06, + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "input_dbu_cost_per_token": 2.5e-05, + "litellm_provider": "databricks", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "output_dbu_cost_per_token": 0.0002, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "databricks/databricks-gpt-5-4": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5000020000000002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-4-mini": { + "cache_creation_input_token_cost": 7.4998e-07, + "cache_read_input_token_cost": 7.497e-08, + "input_cost_per_token": 7.4998e-07, + "input_dbu_cost_per_token": 1.0714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 4.50002e-06, + "output_dbu_cost_per_token": 6.4286e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-4-nano": { + "cache_creation_input_token_cost": 1.9999e-07, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 1.9999e-07, + "input_dbu_cost_per_token": 2.857e-06, + "litellm_provider": "databricks", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.24999e-06, + "output_dbu_cost_per_token": 1.7857e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-sol": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 3.9998e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-terra": { + "cache_creation_input_token_cost": 3.12501e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-luna": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.99998e-06, + "output_dbu_cost_per_token": 8.5714e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 2.999997e-05, + "output_dbu_cost_per_token": 0.000428571, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_dbu_cost_per_token": 0.000428571, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.00018000003, + "output_dbu_cost_per_token": 0.002571429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-mini": { + "cache_creation_input_token_cost": 2.4997e-07, + "cache_read_input_token_cost": 2.499e-08, "input_cost_per_token": 2.4997000000000006e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", @@ -13573,9 +20525,14 @@ "mode": "chat", "output_cost_per_token": 1.9999700000000004e-06, "output_dbu_cost_per_token": 2.8571e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-nano": { + "cache_creation_input_token_cost": 4.998e-08, + "cache_read_input_token_cost": 4.97e-09, "input_cost_per_token": 4.998e-08, "input_dbu_cost_per_token": 7.14e-07, "litellm_provider": "databricks", @@ -13588,9 +20545,14 @@ "mode": "chat", "output_cost_per_token": 3.9998000000000007e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving" + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -13606,6 +20568,8 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-gpt-oss-20b": { + "cache_creation_input_token_cost": 7e-08, + "cache_read_input_token_cost": 7e-08, "input_cost_per_token": 7e-08, "input_dbu_cost_per_token": 1e-06, "litellm_provider": "databricks", @@ -13620,7 +20584,35 @@ "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-grok-4-6": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.000107143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "databricks/databricks-gte-large-en": { + "cache_creation_input_token_cost": 1.2999e-07, + "cache_read_input_token_cost": 1.2999e-07, "input_cost_per_token": 1.2999000000000001e-07, "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", @@ -13635,23 +20627,66 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, - "databricks/databricks-llama-2-70b-chat": { - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, + "databricks/databricks-inkling": { + "cache_creation_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost": 1.7003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.5000300000000002e-06, - "output_dbu_cost_per_token": 2.1429e-05, + "output_cost_per_token": 4.04999e-06, + "output_dbu_cost_per_token": 5.7857e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, + "databricks/databricks-kimi-k3": { + "cache_creation_input_token_cost": 2.99999e-06, + "cache_read_input_token_cost": 3.0002e-07, + "input_cost_per_token": 2.99999e-06, + "input_dbu_cost_per_token": 4.2857e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-llama-4-maverick": { + "cache_creation_input_token_cost": 5.0001e-07, + "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -13667,23 +20702,9 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "input_cost_per_token": 5.00003e-06, - "input_dbu_cost_per_token": 7.1429e-05, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 1.5000020000000002e-05, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-meta-llama-3-1-8b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, "input_cost_per_token": 1.5000999999999998e-07, "input_dbu_cost_per_token": 2.1429999999999996e-06, "litellm_provider": "databricks", @@ -13699,6 +20720,8 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "databricks/databricks-meta-llama-3-3-70b-instruct": { + "cache_creation_input_token_cost": 5.0001e-07, + "cache_read_input_token_cost": 5.0001e-07, "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -13714,69 +20737,73 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "databricks/databricks-qwen35-122b-a10b": { + "cache_creation_input_token_cost": 2.2001e-07, + "cache_read_input_token_cost": 2.2001e-07, + "input_cost_per_token": 2.2001e-07, + "input_dbu_cost_per_token": 3.143e-06, "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 25000, + "max_tokens": 25000, "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 2.9999900000000002e-06, - "output_dbu_cost_per_token": 4.2857e-05, + "output_cost_per_token": 2.20003e-06, + "output_dbu_cost_per_token": 3.1429e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true }, - "databricks/databricks-mixtral-8x7b-instruct": { - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, + "databricks/databricks-qwen3-next-80b-a3b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false }, - "databricks/databricks-mpt-30b-instruct": { - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, + "databricks/databricks-qwen3-embedding-0-6b": { + "cache_creation_input_token_cost": 2.002e-08, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 2.002e-08, + "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 32768, + "max_tokens": 32768, "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, - "mode": "chat", - "output_cost_per_token": 1.00002e-06, - "output_dbu_cost_per_token": 1.4286e-05, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", + "mode": "embedding", "output_cost_per_token": 0.0, "output_dbu_cost_per_token": 0.0, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, "dataforseo/search": { "input_cost_per_query": 0.003, @@ -13784,13 +20811,17 @@ "mode": "search" }, "davinci-002": { + "deprecation_date": "2026-09-28", "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "source": "https://developers.openai.com/api/docs/pricing" }, "deepgram/base": { "input_cost_per_second": 0.00020833, @@ -14212,6 +21243,96 @@ "/v1/audio/transcriptions" ] }, + "deepgram/streaming/nova-3": { + "input_cost_per_second": 8e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0048/60 seconds = $0.00008000 per second", + "note": "Nova-3 monolingual streaming, pay as you go", + "original_pricing_per_minute": 0.0048 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, + "deepgram/streaming/nova-3-multilingual": { + "input_cost_per_second": 9.667e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0058/60 seconds = $0.00009667 per second", + "note": "Nova-3 multilingual (language=multi) streaming, pay as you go", + "original_pricing_per_minute": 0.0058 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, + "deepgram/streaming/redact": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0020/60 seconds = $0.00003333 per second", + "note": "Redaction add-on (redact query param), streaming, pay as you go", + "original_pricing_per_minute": 0.002 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, + "deepgram/streaming/keyterm": { + "input_cost_per_second": 2.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0013/60 seconds = $0.00002167 per second", + "note": "Keyterm Prompting add-on (keyterm query param), streaming, pay as you go", + "original_pricing_per_minute": 0.0013 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, + "deepgram/streaming/detect_entities": { + "input_cost_per_second": 2.833e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0017/60 seconds = $0.00002833 per second", + "note": "Entity Detection add-on (detect_entities query param), streaming, pay as you go", + "original_pricing_per_minute": 0.0017 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, + "deepgram/streaming/diarize": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0020/60 seconds = $0.00003333 per second", + "note": "Speaker Diarization add-on (diarize / diarize_model query params), streaming, pay as you go", + "original_pricing_per_minute": 0.002 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/listen" + ] + }, "deepgram/whisper": { "input_cost_per_second": 0.0001, "litellm_provider": "deepgram", @@ -14294,12 +21415,13 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 9e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 131072, @@ -14316,11 +21438,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { "max_tokens": 131072, @@ -14337,12 +21460,13 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_tokens": 32768, @@ -14370,12 +21494,13 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 6e-08, + "input_cost_per_token": 1.2e-07, "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_tokens": 40960, @@ -14393,11 +21518,12 @@ "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, - "output_cost_per_token": 6e-07, + "output_cost_per_token": 5.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -14414,23 +21540,25 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.9e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 8e-08, "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_tokens": 262144, @@ -14447,23 +21575,27 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 1.2e-06, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 1.4e-06, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_tokens": 262144, @@ -14490,11 +21622,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, + "input_cost_per_token": 8.5e-07, + "output_cost_per_token": 8.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { "max_tokens": 131072, @@ -14620,36 +21753,41 @@ "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 3.8e-07, + "input_cost_per_token": 3.2e-07, "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 8.8e-07, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1.35e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 9.5e-07, "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_tokens": 163840, @@ -14663,18 +21801,6 @@ "supports_tool_choice": true, "supports_function_calling": true }, - "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true - }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, "max_input_tokens": 1000000, @@ -14685,7 +21811,11 @@ "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { "max_tokens": 1000000, @@ -14696,9 +21826,37 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true, + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-3-27b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 1.6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true, + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-3-4b-it": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, @@ -14707,29 +21865,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true - }, - "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true - }, - "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_tokens": 131072, @@ -14767,34 +21904,37 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_tokens": 131072, @@ -14842,12 +21982,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 131072, @@ -14865,11 +22006,12 @@ "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, - "output_cost_per_token": 3e-08, + "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_tokens": 65536, @@ -14896,12 +22038,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 4e-08, + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_tokens": 32768, @@ -14981,6 +22124,19 @@ "supports_tool_choice": true, "supports_function_calling": true }, + "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { + "max_input_tokens": 262144, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "source": "https://deepinfra.com/pricing", + "supports_tool_choice": true, + "supports_function_calling": true, + "supports_reasoning": true, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true + }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -14996,23 +22152,25 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4.5e-07, + "input_cost_per_token": 3.7e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.5e-07, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -15028,6 +22186,7 @@ "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -15050,6 +22209,7 @@ "supports_tool_choice": true }, "deepseek/deepseek-coder": { + "cache_read_input_token_cost": 1.4e-08, "input_cost_per_token": 1.4e-07, "input_cost_per_token_cache_hit": 1.4e-08, "litellm_provider": "deepseek", @@ -15064,6 +22224,7 @@ "supports_tool_choice": true }, "deepseek/deepseek-r1": { + "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 5.5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "deepseek", @@ -15080,6 +22241,7 @@ }, "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -15119,6 +22281,7 @@ "supports_tool_choice": true }, "deepseek/deepseek-v3.2": { + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -15141,6 +22304,7 @@ "max_tokens": 81920, "mode": "chat", "output_cost_per_token": 1.68e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -15149,15 +22313,19 @@ "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 164000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "dolphin": { "input_cost_per_token": 5e-07, @@ -15374,6 +22542,265 @@ "litellm_provider": "perplexity", "mode": "search" }, + "sail/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_balanced": 2e-06, + "output_cost_per_token_balanced": 1e-05, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_flex": 6.25e-06, + "cache_read_input_token_cost_flex": 1.5e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.8e-07, + "output_cost_per_token": 3.08e-06, + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token_balanced": 5e-07, + "output_cost_per_token_balanced": 2.5e-06, + "cache_read_input_token_cost_balanced": 1.2e-07, + "input_cost_per_token_flex": 4e-07, + "output_cost_per_token_flex": 1.8e-06, + "cache_read_input_token_cost_flex": 8e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.5e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 8e-08, + "output_cost_per_token_balanced": 2.8e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.8e-07, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.2e-07, + "output_cost_per_token": 2.77e-06, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token_balanced": 7.4e-07, + "output_cost_per_token_balanced": 2.22e-06, + "cache_read_input_token_cost_balanced": 3e-08, + "input_cost_per_token_flex": 4.6e-07, + "output_cost_per_token_flex": 1.39e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 1.4e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 9e-08, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 4.8e-07, + "cache_read_input_token_cost_balanced": 5e-09, + "input_cost_per_token_flex": 8e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 4e-09, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 4.5e-07, + "output_cost_per_token_balanced": 3e-06, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 3.5e-07, + "output_cost_per_token_flex": 2e-06, + "cache_read_input_token_cost_flex": 1e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-31B-it": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 6e-07, + "cache_read_input_token_cost_balanced": 8e-08, + "input_cost_per_token_flex": 6e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/nvidia/Gemma-4-31B-IT-NVFP4": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token_balanced": 1.1e-07, + "output_cost_per_token_balanced": 3.2e-07, + "cache_read_input_token_cost_balanced": 6e-08, + "input_cost_per_token_flex": 7e-08, + "output_cost_per_token_flex": 2e-07, + "cache_read_input_token_cost_flex": 4e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-12B-it": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token_balanced": 1e-07, + "output_cost_per_token_balanced": 2e-06, + "cache_read_input_token_cost_balanced": 7e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 4e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, "searxng/search": { "litellm_provider": "searxng", "mode": "search", @@ -15406,6 +22833,22 @@ "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } }, + "agentcore/search": { + "input_cost_per_query": 0.0, + "litellm_provider": "agentcore", + "mode": "search", + "metadata": { + "notes": "Web Search on Amazon Bedrock AgentCore, billed by AWS on the gateway" + } + }, + "bing_grounding/search": { + "input_cost_per_query": 0.014, + "litellm_provider": "bing_grounding", + "mode": "search", + "metadata": { + "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." + } + }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", @@ -15414,6 +22857,14 @@ "notes": "TinyFish Search API" } }, + "nimble/search": { + "input_cost_per_query": 0.005, + "litellm_provider": "nimble", + "mode": "search", + "metadata": { + "notes": "Nimble Search API pay-as-you-go list price: $5 per 1,000 searches, up to 100 results per search. Volume plans price differently." + } + }, "elevenlabs/scribe_v1": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", @@ -15470,27 +22921,11 @@ "/v1/audio/speech" ] }, - "embed-english-light-v2.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, - "embed-english-v2.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -15498,8 +22933,8 @@ "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -15508,19 +22943,11 @@ "supports_embedding_image_input": true, "supports_image_input": true }, - "embed-multilingual-v2.0": { - "input_cost_per_token": 1e-07, - "litellm_provider": "cohere", - "max_input_tokens": 768, - "max_tokens": 768, - "mode": "embedding", - "output_cost_per_token": 0.0 - }, "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -15528,13 +22955,14 @@ "embed-multilingual-light-v3.0": { "input_cost_per_token": 0.0001, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true }, "eu.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.95e-08, "input_cost_per_token": 7.8e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -15546,9 +22974,11 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "eu.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 1.15e-08, "input_cost_per_token": 4.6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -15558,9 +22988,11 @@ "output_cost_per_token": 1.84e-07, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_tool_choice": true }, "eu.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.625e-07, "input_cost_per_token": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -15573,24 +23005,25 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.25e-06, + "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07, + "cache_read_input_token_cost": 8e-08, + "cache_creation_input_token_cost": 1e-06, "prompt_cache_min_tokens": 2048 }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { @@ -15600,12 +23033,13 @@ "input_cost_per_token": 1.1e-06, "deprecation_date": "2026-10-15", "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -15617,7 +23051,9 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-07, + "output_cost_per_token_batches": 2.75e-06 }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -15674,22 +23110,6 @@ "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3.75e-06 }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -15705,22 +23125,6 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, @@ -15745,7 +23149,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "deprecation_date": "2027-01-08" }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -15776,6 +23181,7 @@ "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-14", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -15802,7 +23208,8 @@ "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -15815,6 +23222,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -15836,7 +23244,10 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.65e-06, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-07, @@ -15919,6 +23330,166 @@ "/v1/images/generations" ] }, + "fal_ai/bytedance/seedance-2.5/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/image-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.5/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.473, + "output_cost_per_second_480p": 0.2205, + "output_cost_per_second_720p": 0.473, + "source": "https://fal.ai/models/bytedance/seedance-2.5/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.06, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_4k": 0.16, + "source": "https://fal.ai/models/minimax/h3/text-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/minimax/h3/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.13, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.06, + "output_cost_per_second_2k": 0.13, + "output_cost_per_second_4k": 0.16, + "source": "https://fal.ai/models/minimax/h3/reference-to-video", + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/text-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.3034, + "output_cost_per_second_480p": 0.1346, + "output_cost_per_second_720p": 0.3034, + "output_cost_per_second_1080p": 0.682, + "output_cost_per_second_4k": 1.5552, + "source": "https://fal.ai/models/bytedance/seedance-2.0/text-to-video", + "metadata": { + "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" + }, + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/image-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.3034, + "output_cost_per_second_480p": 0.1346, + "output_cost_per_second_720p": 0.3034, + "output_cost_per_second_1080p": 0.682, + "output_cost_per_second_4k": 1.5552, + "source": "https://fal.ai/models/bytedance/seedance-2.0/image-to-video", + "metadata": { + "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" + }, + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "fal_ai/bytedance/seedance-2.0/reference-to-video": { + "litellm_provider": "fal_ai", + "mode": "video_generation", + "output_cost_per_second": 0.3034, + "output_cost_per_second_480p": 0.1346, + "output_cost_per_second_720p": 0.3034, + "output_cost_per_second_1080p": 0.682, + "output_cost_per_second_4k": 1.5552, + "source": "https://fal.ai/models/bytedance/seedance-2.0/reference-to-video", + "metadata": { + "comment": "fal bills $0.014 per 1k tokens (480p/720p/1080p) and $0.008 per 1k tokens (4k) with tokens = h*w*seconds*24/1024; 480p and 4k rates derived from that formula at 854x480 and 3840x2160" + }, + "supported_endpoints": [ + "/v1/videos" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, "fal_ai/fal-ai/ideogram/v3": { "litellm_provider": "fal_ai", "mode": "image_generation", @@ -15983,6 +23554,1989 @@ "/v1/images/generations" ] }, + "fal_ai/fal-ai/nano-banana-2": { + "litellm_provider": "fal_ai", + "metadata": { + "comment": "priced by the request's resolution field (0.5K, 1K default, 2K, 4K); the web search and high thinking surcharges are not modeled" + }, + "mode": "image_generation", + "output_cost_per_image": 0.08, + "output_cost_per_image_0.5K": 0.06, + "output_cost_per_image_1K": 0.08, + "output_cost_per_image_2K": 0.12, + "output_cost_per_image_4K": 0.16, + "source": "https://fal.ai/models/fal-ai/nano-banana-2", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/nano-banana-pro": { + "litellm_provider": "fal_ai", + "metadata": { + "comment": "priced by the request's resolution field (1K default, 2K, 4K); the web search surcharge is not modeled" + }, + "mode": "image_generation", + "output_cost_per_image": 0.15, + "output_cost_per_image_1K": 0.15, + "output_cost_per_image_2K": 0.15, + "output_cost_per_image_4K": 0.3, + "source": "https://fal.ai/models/fal-ai/nano-banana-pro", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "OpenAI gpt-image-2 served through fal.ai. fal bills by token but publishes deterministic per-image prices per size and quality, mirrored here as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2 that litellm's fal_ai cost calculator picks from the request params. This flat entry is the fallback when no keyed entry matches and carries the default request rate (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" + }, + "mode": "image_generation", + "output_cost_per_image": 0.145, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.007, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.012, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.037, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.056, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.101, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.145, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.211, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.165, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.158, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.222, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.401, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/gpt-image-2": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "Alias of fal_ai/openai/gpt-image-2, which litellm also accepts without the openai/ prefix. Same rates, including the keyed fal_ai/{quality}/{width}-x-{height}/gpt-image-2 entries; see that entry for details" + }, + "mode": "image_generation", + "output_cost_per_image": 0.145, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.006, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.005, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.007, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.012, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.037, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.056, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.101, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.145, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.211, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.165, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.158, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.222, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/gpt-image-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.401, + "source": "https://fal.ai/models/openai/gpt-image-2", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "Editing endpoint of gpt-image-2 on fal.ai, reached through the image generation path with fal's image_urls param since /v1/images/edits is not wired for fal_ai. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" + }, + "mode": "image_generation", + "output_cost_per_image": 0.151, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.011, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.015, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.018, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.017, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.019, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.024, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.043, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.061, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.054, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.068, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.113, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.151, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.219, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.178, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.158, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.234, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.413, + "source": "https://fal.ai/models/openai/gpt-image-2/edit", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "OpenAI gpt-image-2.5 (flare) served through fal.ai. fal publishes deterministic per-image prices per size and quality, mirrored as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/flare/text-to-image that the fal_ai cost calculator picks from the request params. This flat entry is the fallback for the default request (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" + }, + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00402, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00588, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00474, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00441, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00615, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01113, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00903, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01317, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01434, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02595, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05268, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04116, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0396, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05529, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.10008, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0642, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09366, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07377, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07041, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09828, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1779, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-768/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.14445, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21072, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.16464, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1584, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.2211, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/flare/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.40026, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "Editing endpoint of gpt-image-2.5 (flare) on fal.ai, reachable through /v1/images/edits or the image generation path with fal's image_urls param. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/flare/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" + }, + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00402, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00588, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00474, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00441, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00615, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01113, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00903, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01317, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01434, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02595, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05268, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04116, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0396, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05529, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.10008, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0642, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09366, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07377, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07041, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09828, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1779, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-768/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.14445, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21072, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.16464, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1584, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.2211, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/flare/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.40026, + "source": "https://fal.ai/models/openai/gpt-image-2.5/flare/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "OpenAI gpt-image-2.5 (sunburst) served through fal.ai. fal publishes deterministic per-image prices per size and quality, mirrored as keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/sunburst/text-to-image that the fal_ai cost calculator picks from the request params. This flat entry is the fallback for the default request (quality=high, image_size=landscape_4_3 at 1024x768). quality=auto is priced as high" + }, + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00402, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00588, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00474, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00441, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00615, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01113, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00903, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01317, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01434, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02595, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05268, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04116, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0396, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05529, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.10008, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0642, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09366, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07377, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07041, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09828, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1779, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-768/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.14445, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21072, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.16464, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1584, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.2211, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/sunburst/text-to-image": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.40026, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/text-to-image", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "Editing endpoint of gpt-image-2.5 (sunburst) on fal.ai, reachable through /v1/images/edits or the image generation path with fal's image_urls param. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2.5/sunburst/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)" + }, + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00402, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00588, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00474, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00441, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00615, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/low/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01113, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.00903, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01317, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01029, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.01434, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/medium/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02595, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.03612, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05268, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04116, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0396, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.05529, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/high/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.10008, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.0642, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09366, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07377, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.07041, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.09828, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/xhigh/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1779, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-768/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.14445, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1024/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.21072, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1024-x-1536/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.16464, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/1920-x-1080/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.1584, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/2560-x-1440/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.2211, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/max/3840-x-2160/openai/gpt-image-2.5/sunburst/edit": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.40026, + "source": "https://fal.ai/models/openai/gpt-image-2.5/sunburst/edit", + "supported_endpoints": [ + "/v1/images/edits", + "/v1/images/generations" + ], + "supports_vision": true + }, + "fal_ai/fal-ai/flux/dev": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "fal bills FLUX.1 [dev] at $0.025 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price is the fallback when dimensions are unavailable" + }, + "mode": "image_generation", + "output_cost_per_image": 0.025, + "output_cost_per_pixel": 2.384185791015625e-08, + "source": "https://fal.ai/models/fal-ai/flux/dev", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "fal_ai/fal-ai/trellis": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://fal.ai/models/fal-ai/trellis", + "metadata": { + "comment": "image-to-3D, returns a GLB mesh; served through the /fal_ai pass-through route" + } + }, + "fal_ai/fal-ai/trellis-2": { + "litellm_provider": "fal_ai", + "mode": "image_generation", + "output_cost_per_image": 0.3, + "output_cost_per_image_512": 0.25, + "output_cost_per_image_1024": 0.3, + "output_cost_per_image_1536": 0.35, + "source": "https://fal.ai/models/fal-ai/trellis-2", + "metadata": { + "comment": "image-to-3D, returns a GLB mesh; priced by the request's resolution field (default 1024); served through the /fal_ai pass-through route" + } + }, + "fal_ai/fal-ai/flux-lora-depth": { + "litellm_provider": "fal_ai", + "metadata": { + "notes": "fal bills fal-ai/flux-lora-depth at $0.035 per megapixel, rounding each image up to the nearest megapixel. The per-pixel rate is used when Fal reports the output size, and the flat per-image price prices the default 1 MP output like the sibling flux entries" + }, + "mode": "image_generation", + "output_cost_per_image": 0.035, + "output_cost_per_pixel": 3.337860107421875e-08, + "source": "https://fal.ai/models/fal-ai/flux-lora-depth", + "supported_endpoints": [ + "/v1/images/edits" + ] + }, + "fal_ai/fal-ai/moondream3-preview/query": { + "input_cost_per_token": 4e-07, + "litellm_provider": "fal_ai", + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://fal.ai/models/fal-ai/moondream3-preview/query", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_reasoning": true, + "supports_vision": true + }, "featherless_ai/featherless-ai/Qwerky-72B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, @@ -16033,9 +25587,10 @@ "output_cost_per_token": 5e-07 }, "fireworks-ai-up-to-4b": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "output_cost_per_token": 2e-07 + "output_cost_per_token": 1e-07, + "source": "https://docs.fireworks.ai/serverless/pricing" }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { "input_cost_per_token": 1.6e-08, @@ -16175,16 +25730,40 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-07, - "input_cost_per_token": 1.74e-06, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "cache_read_input_token_cost_priority": 5.5e-08, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_priority": 1.65e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 3.96e-06, + "output_cost_per_token_priority": 4.95e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "cache_read_input_token_cost_priority": 5.5e-08, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "output_cost_per_token_priority": 4.95e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16279,14 +25858,18 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16295,14 +25878,17 @@ }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 7.2e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16370,8 +25956,8 @@ "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -16381,14 +25967,18 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, + "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16397,14 +25987,18 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, + "cache_read_input_token_cost_priority": 2.85e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, + "input_cost_per_token_priority": 1.425e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16528,37 +26122,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 1.8e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, @@ -16628,22 +26209,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-07, - "input_cost_per_token": 1.74e-06, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, @@ -16693,14 +26258,18 @@ }, "fireworks_ai/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16709,14 +26278,17 @@ }, "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 7.2e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16744,8 +26316,8 @@ "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -16755,14 +26327,18 @@ }, "fireworks_ai/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, + "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16771,11 +26347,12 @@ }, "fireworks_ai/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -16787,14 +26364,18 @@ }, "fireworks_ai/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, + "cache_read_input_token_cost_priority": 2.85e-07, + "deprecation_date": "2026-09-25", "input_cost_per_token": 9.5e-07, + "input_cost_per_token_priority": 1.425e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16803,11 +26384,12 @@ }, "fireworks_ai/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -16831,37 +26413,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/minimax-m2p7": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 9e-08, "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 1.8e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, @@ -16872,7 +26441,7 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -16915,57 +26484,212 @@ "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" }, - "friendliai/meta-llama-3.1-70b-instruct": { - "input_cost_per_token": 6e-07, + "friendliai/zai-org/GLM-5.3-Flash": { "litellm_provider": "friendliai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_image_input": true, + "supports_video_input": true, + "mode": "chat", + "comment": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", + "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/meta-llama-3.1-8b-instruct": { - "input_cost_per_token": 1e-07, + "friendliai/zai-org/GLM-5.3": { "litellm_provider": "friendliai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1e-07, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "input_cost_per_token": 1.26e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 2.34e-07, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/google/gemma-4-31B-it": { + "litellm_provider": "friendliai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4e-07, + "supports_prompt_caching": false, + "supports_reasoning": true, + "reasoning_effort_levels": [], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_image_input": true, + "supports_video_input": false, + "mode": "chat", + "comment": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/zai-org/GLM-5.2": { + "litellm_provider": "friendliai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "high", + "max" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/deepseek-ai/DeepSeek-V3.2": { + "litellm_provider": "friendliai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "DeepSeek chat model for instruction following, coding, and analysis", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/MiniMaxAI/MiniMax-M2.5": { + "litellm_provider": "friendliai", + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "max_tokens": 196608, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/zai-org/GLM-5.1": { + "litellm_provider": "friendliai", + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "max_tokens": 202752, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", + "source": "https://api.friendli.ai/serverless/v1/models" }, "ft:babbage-002": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_batches": 8e-07, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, - "output_cost_per_token_batches": 2e-07 + "output_cost_per_token_batches": 9e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "ft:davinci-002": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.2e-05, - "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_batches": 6e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, - "output_cost_per_token_batches": 1e-06 + "output_cost_per_token_batches": 6e-06, + "source": "https://developers.openai.com/api/docs/pricing" }, "ft:gpt-3.5-turbo": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", @@ -16975,10 +26699,12 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_batches": 3e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_system_messages": true, "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0125": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -16990,6 +26716,7 @@ "supports_tool_choice": true }, "ft:gpt-3.5-turbo-0613": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 4096, @@ -17001,6 +26728,7 @@ "supports_tool_choice": true }, "ft:gpt-3.5-turbo-1106": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -17012,6 +26740,7 @@ "supports_tool_choice": true }, "ft:gpt-4-0613": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -17026,15 +26755,17 @@ }, "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, + "cache_read_input_token_cost_batches": 9e-07, "input_cost_per_token": 3.75e-06, - "input_cost_per_token_batches": 1.875e-06, + "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, - "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_batches": 1.25e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -17063,6 +26794,7 @@ }, "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", @@ -17072,6 +26804,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -17082,6 +26815,7 @@ }, "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", @@ -17091,6 +26825,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -17100,6 +26835,7 @@ }, "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", @@ -17109,6 +26845,7 @@ "mode": "chat", "output_cost_per_token": 3.2e-06, "output_cost_per_token_batches": 1.6e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -17118,6 +26855,8 @@ }, "ft:gpt-4.1-nano-2025-04-14": { "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, + "deprecation_date": "2026-10-23", "input_cost_per_token": 2e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", @@ -17127,6 +26866,7 @@ "mode": "chat", "output_cost_per_token": 8e-07, "output_cost_per_token_batches": 4e-07, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -17136,6 +26876,8 @@ }, "ft:o4-mini-2025-04-16": { "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "deprecation_date": "2026-10-23", "input_cost_per_token": 4e-06, "input_cost_per_token_batches": 2e-06, "litellm_provider": "openai", @@ -17145,6 +26887,7 @@ "mode": "chat", "output_cost_per_token": 1.6e-05, "output_cost_per_token_batches": 8e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -17152,154 +26895,12 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-001": { - "cache_read_input_token_cost": 3.75e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-07, + "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_flex": 3e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", @@ -17309,7 +26910,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17341,12 +26942,23 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, "supports_image_size": false }, "gemini-2.5-flash-image": { - "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2027-03-15", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -17356,8 +26968,10 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17388,9 +27002,20 @@ "supports_image_size": false }, "gemini-3-pro-image": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -17399,8 +27024,12 @@ "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17429,7 +27058,15 @@ }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, @@ -17439,6 +27076,9 @@ "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ @@ -17468,8 +27108,14 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -17478,7 +27124,9 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17507,7 +27155,10 @@ }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -17516,6 +27167,7 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", @@ -17543,6 +27195,49 @@ }, "web_search_billing_unit": "per_query" }, + "gemini-3.1-flash-lite-image": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "deprecation_date": "2027-06-28", + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true + }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, @@ -17589,10 +27284,14 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-08, + "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -17600,6 +27299,7 @@ "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -17610,7 +27310,7 @@ "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17645,9 +27345,71 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 + }, + "gemini-3.5-flash-lite": { + "deprecation_date": "2027-07-21", + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, + "cache_read_input_token_cost_flex": 1.5e-08, + "cache_read_input_token_cost_priority": 5.4e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "deep-research-pro-preview-12-2025": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -17660,7 +27422,7 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17682,7 +27444,11 @@ "supports_web_search": true }, "gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-08, + "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", @@ -17692,7 +27458,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17724,6 +27490,15 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-08, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, + "input_cost_per_audio_token_priority": 5.4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, "supports_image_size": false }, "gemini-2.5-flash-lite-preview-09-2025": { @@ -17769,10 +27544,11 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, "gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", @@ -17782,7 +27558,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17814,12 +27590,59 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, - "gemini-live-2.5-flash-preview-native-audio-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "gemini-live-2.5-flash-native-audio": { + "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/vertex_ai/live", + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": false, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.035, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.035 + }, + "gemini_native_audio": true, + "input_cost_per_image_token": 3e-06, + "input_cost_per_video_token": 3e-06 + }, + "gemini-live-2.5-flash-preview-native-audio-09-2025": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -17827,7 +27650,7 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live" ], @@ -17846,7 +27669,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -17858,12 +27681,12 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "gemini_native_audio": true + "gemini_native_audio": true, + "input_cost_per_image_token": 3e-06 }, "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": { - "cache_read_input_token_cost": 7.5e-08, "input_cost_per_audio_token": 3e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -17891,7 +27714,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -17906,56 +27729,14 @@ }, "gemini_native_audio": true }, - "gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "supports_image_size": false - }, "gemini-2.5-pro": { + "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, + "cache_read_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai-language-models", @@ -17965,7 +27746,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -17983,6 +27764,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, @@ -17994,65 +27776,19 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } - }, - "gemini-3-pro-preview": { - "deprecation_date": "2026-03-26", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.25e-06, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05 }, "gemini-3.1-pro-preview": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -18068,7 +27804,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18102,14 +27838,19 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-3.1-pro-preview-customtools": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -18158,7 +27899,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -18216,7 +27958,9 @@ "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_token": 5e-07, "input_cost_per_audio_token": 1e-06, "litellm_provider": "vertex_ai", @@ -18225,7 +27969,7 @@ "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18261,12 +28005,21 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06 }, "vertex_ai/gemini-3.5-flash": { + "prompt_cache_min_tokens": 4096, + "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "input_cost_per_token": 1.5e-06, - "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token": 1.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -18274,7 +28027,8 @@ "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18304,7 +28058,7 @@ "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_priority": 2.7e-06, "output_cost_per_token_priority": 1.62e-05, "cache_read_input_token_cost_priority": 2.7e-07, "search_context_cost_per_query": { @@ -18312,9 +28066,278 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_batches": 4.5e-06, + "input_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_flex": 4.5e-06, + "cache_read_input_token_cost_flex": 7.5e-08 + }, + "vertex_ai/gemini-3.6-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "vertex_ai/gemini-3.7-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "vertex_ai/gemini-3.8-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "vertex_ai/gemini-3.8-flash-cyber": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 7.5e-06, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false, + "supports_native_streaming": true + }, + "vertex_ai/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "input_cost_per_video_token": 1e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/vertex_ai/live", + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "output_cost_per_video_token": 1e-06 }, "vertex_ai/gemini-3.1-pro-preview": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -18330,7 +28353,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18364,14 +28387,19 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "vertex_ai/gemini-3.1-pro-preview-customtools": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -18426,22 +28454,22 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -18499,49 +28527,55 @@ "supports_url_context": true, "supports_vision": true }, - "gemini/gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "input_cost_per_token": 3e-07, + "gemini/gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image", - "video", - "audio" + "audio", + "video" ], "supported_output_modalities": [ "text" ], + "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "tpm": 250000, - "rpm": 10, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "web_search_billing_unit": "per_query" }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 1.25e-06, @@ -18553,7 +28587,7 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -18568,7 +28602,9 @@ "supports_vision": true }, "gemini-embedding-001": { + "deprecation_date": "2028-05-20", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, "max_tokens": 2048, @@ -18578,10 +28614,14 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "gemini-embedding-2-preview": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, @@ -18592,25 +28632,33 @@ "uses_embed_content": true }, "gemini-embedding-2": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true }, "vertex_ai/gemini-embedding-2-preview": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, @@ -18622,17 +28670,21 @@ "uses_embed_content": true }, "vertex_ai/gemini-embedding-2": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true }, @@ -18650,6 +28702,7 @@ "uses_embed_content": true }, "gemini/gemini-embedding-001": { + "deprecation_date": "2028-05-14", "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, @@ -18661,27 +28714,15 @@ "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "tpm": 10000000 }, - "gemini/gemini-embedding-2-preview": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, - "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_multimodal": true, - "tpm": 10000000 - }, "gemini/gemini-embedding-2": { - "input_cost_per_audio_per_second": 0.00016, - "input_cost_per_image": 0.00012, + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, "input_cost_per_token": 2e-07, - "input_cost_per_video_per_second": 0.00079, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, "max_tokens": 8192, @@ -18690,114 +28731,131 @@ "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supports_multimodal": true, - "tpm": 10000000 - }, - "gemini/gemini-1.5-flash": { - "deprecation_date": "2025-09-29", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 8192, - "max_tokens": 8192, - "mode": "embedding", - "output_cost_per_token": 0, - "output_vector_size": 3072, - "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", - "supports_multimodal": true, - "tpm": 10000000 - }, - "gemini/gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, + "supports_multimodal": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "tpm": 10000000 }, - "gemini/gemini-2.0-flash-001": { - "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, + "gemini/gemini-3-pro-image-preview": { + "deprecation_date": "2026-06-25", + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-07, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_image_token": 0.00012, + "output_cost_per_token": 1.2e-05, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], "supported_modalities": [ "text", - "image", - "audio", - "video" + "image" ], "supported_output_modalities": [ "text", "image" ], - "supports_audio_output": false, - "supports_function_calling": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "tpm": 10000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_reasoning": false }, - "gemini/gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, + "gemini/gemini-3.1-flash-image-preview": { + "deprecation_date": "2026-06-25", + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "image_generation", + "output_cost_per_image": 0.045, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "rpm": 1000, + "tpm": 4000000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_audio_token_cost": 5e-08, + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-05-25", + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 8192, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], "supported_modalities": [ "text", "image", @@ -18807,15 +28865,121 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": true, + "supports_audio_input": true, + "supports_audio_output": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, "supports_vision": true, "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 + }, + "gemini/gemini-embedding-2-preview": { + "input_cost_per_audio_token": 6.5e-06, + "input_cost_per_audio_token_batches": 3.25e-06, + "input_cost_per_image_token": 4.5e-07, + "input_cost_per_image_token_batches": 2.25e-07, + "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_video_token": 1.2e-05, + "input_cost_per_video_token_batches": 6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_multimodal": true, + "supports_vision": true, + "tpm": 10000000 + }, + "gemini/deep-research-preview-04-2026": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "rpm": 1000, "tpm": 4000000, + "output_cost_per_token_batches": 6e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.035, + "search_context_size_medium": 0.035, + "search_context_size_high": 0.035 + } + }, + "gemini/deep-research-max-preview-04-2026": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 6e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, @@ -18823,18 +28987,22 @@ } }, "gemini/gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 3e-08, + "cache_read_input_token_cost_flex": 3e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18867,15 +29035,29 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-02", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, "litellm_provider": "gemini", "supports_reasoning": false, - "max_input_tokens": 32768, + "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", @@ -18884,7 +29066,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18901,28 +29083,31 @@ "image" ], "supports_audio_output": false, - "supports_function_calling": true, + "supports_function_calling": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, + "supports_web_search": false, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "supports_audio_input": false, "supports_image_size": false }, "gemini/gemini-3-pro-image": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -18934,7 +29119,9 @@ "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -18949,8 +29136,8 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_prompt_caching": false, + "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, @@ -18960,14 +29147,16 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "supports_reasoning": false + "supports_reasoning": true }, - "gemini/gemini-3-pro-image-preview": { + "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "gemini", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", @@ -18977,6 +29166,8 @@ "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -19006,104 +29197,19 @@ "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-image": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, - "output_cost_per_token": 1.5e-06, - "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3.1-flash-image-preview": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_batches": 1.25e-07, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.045, - "output_cost_per_image_token": 6e-05, - "output_cost_per_token": 1.5e-06, - "output_cost_per_token_batches": 7.5e-07, - "rpm": 1000, - "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/deep-research-pro-preview-12-2025": { - "input_cost_per_image": 0.0011, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, - "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, - "output_cost_per_token_batches": 6e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -19119,6 +29225,87 @@ "image" ], "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_pdf_input": true + }, + "gemini/gemini-3.1-flash-lite-image": { + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "rpm": 1000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 4000000 + }, + "gemini/deep-research-pro-preview-12-2025": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 6e-06, + "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, @@ -19128,115 +29315,26 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_pdf_input": true }, "gemini/gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-08, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 1e-08, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 1.8e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19269,21 +29367,89 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_audio_token_priority": 5.4e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.8e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7.2e-07, + "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-flash-latest": { "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-flash-lite-latest": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19312,135 +29478,68 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "supports_image_size": false + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-preview-tts": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "audio_speech", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "tpm": 4000000, - "rpm": 10 + "rpm": 10, + "supports_audio_input": false, + "supports_function_calling": false, + "supports_response_schema": false, + "supports_web_search": false }, "gemini/gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "cache_read_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost_priority": 2.25e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, - "input_cost_per_token_priority": 1.25e-06, - "input_cost_per_token_above_200k_tokens_priority": 2.5e-06, + "input_cost_per_token_priority": 2.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "output_cost_per_token_priority": 1e-05, - "output_cost_per_token_above_200k_tokens_priority": 1.5e-05, + "output_cost_per_token_priority": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 2.7e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -19458,6 +29557,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, @@ -19470,9 +29570,16 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "supports_url_context": true }, "gemini/gemini-2.5-computer-use-preview-10-2025": { + "deprecation_date": "2026-07-28", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", @@ -19483,7 +29590,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/computer-use", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -19502,116 +29609,13 @@ "supports_vision": true, "tpm": 800000 }, - "gemini/gemini-3-pro-preview": { - "deprecation_date": "2026-03-09", - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-05-07", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -19628,7 +29632,7 @@ "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19664,21 +29668,86 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07 + }, + "gemini/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 2e-08, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19716,21 +29785,30 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "supports_audio_input": true }, "gemini/gemini-3.5-flash": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_audio_token": 1e-06, + "cache_read_input_token_cost_batches": 7.5e-08, + "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19762,7 +29840,7 @@ "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_priority": 2.7e-06, "output_cost_per_token_priority": 1.62e-05, "cache_read_input_token_cost_priority": 2.7e-07, "search_context_cost_per_query": { @@ -19770,15 +29848,203 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_batches": 4.5e-06, + "input_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_flex": 4.5e-06, + "cache_read_input_token_cost_flex": 8e-08 + }, + "gemini/gemini-3.6-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "gemini/gemini-3.7-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "gemini/gemini-3.8-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 800000, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "gemini/gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -19786,7 +30052,7 @@ "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions" + "/v1beta/interactions" ], "supported_modalities": [ "text", @@ -19803,9 +30069,11 @@ "supports_system_messages": true, "supports_video_input": true, "supports_vision": true, - "tpm": 800000 + "tpm": 800000, + "deprecation_date": "2026-09-30" }, "gemini/gemini-3.1-pro-preview": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, @@ -19820,7 +30088,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19855,14 +30123,20 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { + "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, @@ -19877,7 +30151,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19912,15 +30186,22 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "cache_read_input_token_cost_priority": 3.6e-07, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_flex": 2e-07, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", @@ -19930,7 +30211,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -19967,7 +30248,13 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06 }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, @@ -19980,7 +30267,7 @@ "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, - "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions" ], @@ -20001,8 +30288,11 @@ "supports_vision": true }, "gemini-3.5-flash": { + "prompt_cache_min_tokens": 4096, + "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_audio_token": 1e-06, + "cache_read_input_token_cost_batches": 7.5e-08, + "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, @@ -20011,7 +30301,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -20042,7 +30332,7 @@ "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 2.7e-06, - "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_audio_token_priority": 2.7e-06, "output_cost_per_token_priority": 1.62e-05, "cache_read_input_token_cost_priority": 2.7e-07, "search_context_cost_per_query": { @@ -20050,23 +30340,254 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_batches": 4.5e-06, + "input_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_flex": 4.5e-06, + "cache_read_input_token_cost_flex": 7.5e-08 + }, + "gemini-3.6-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "gemini-3.7-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "gemini-3.8-flash": { + "prompt_cache_min_tokens": 4096, + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "input_cost_per_token": 7.5e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_priority": 6.75e-06, + "cache_read_input_token_cost_priority": 1.35e-07, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 + }, + "gemini-3.8-flash-cyber": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_flex": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 7.5e-06, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_flex": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_audio_input": true, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_url_context": false, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false, + "supports_native_streaming": true }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], @@ -20074,19 +30595,20 @@ "audio" ], "supports_audio_output": false, - "supports_function_calling": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, + "supports_vision": false, + "supports_web_search": false, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_audio_input": false }, "gemini/gemini-exp-1114": { "input_cost_per_token": 0, @@ -20190,6 +30712,38 @@ "supports_tool_choice": true, "supports_vision": true }, + "gemini/gemma-4-26b-a4b-it": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "gemini", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://ai.google.dev/gemini-api/docs/pricing" + }, + "gemini/gemma-4-31b-it": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "gemini", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://ai.google.dev/gemini-api/docs/pricing" + }, "gemini/imagen-3.0-fast-generate-001": { "litellm_provider": "gemini", "mode": "image_generation", @@ -20202,31 +30756,6 @@ "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "gemini/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-fast-generate-001": { - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-generate-001": { - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-ultra-generate-001": { - "litellm_provider": "gemini", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, "gemini/learnlm-1.5-pro-experimental": { "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, @@ -20302,29 +30831,19 @@ "supports_response_schema": false, "supports_system_messages": false, "supports_vision": false, - "supports_web_search": false - }, - "gemini/veo-2.0-generate-001": { - "litellm_provider": "gemini", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] + "supports_web_search": false, + "output_cost_per_image": 0.08 }, "gemini/veo-3.1-fast-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://ai.google.dev/gemini-api/docs/video", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_4k": 0.3, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], @@ -20333,12 +30852,14 @@ ] }, "gemini/veo-3.1-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, - "source": "https://ai.google.dev/gemini-api/docs/video", + "output_cost_per_second_4k": 0.6, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], @@ -20347,6 +30868,7 @@ ] }, "gemini/veo-3.1-lite-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -20366,8 +30888,10 @@ "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://ai.google.dev/gemini-api/docs/video", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_4k": 0.3, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], @@ -20381,7 +30905,8 @@ "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, - "source": "https://ai.google.dev/gemini-api/docs/video", + "output_cost_per_second_4k": 0.6, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_modalities": [ "text" ], @@ -20390,11 +30915,15 @@ ] }, "github_copilot/claude-haiku-4.5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -20418,6 +30947,7 @@ }, "github_copilot/claude-opus-4.6-fast": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, @@ -20442,11 +30972,15 @@ "supports_vision": true }, "github_copilot/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 1.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], @@ -20467,26 +31001,6 @@ "supports_parallel_function_calling": true, "supports_vision": true }, - "github_copilot/gemini-2.5-pro": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, - "github_copilot/gemini-3-pro-preview": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, "github_copilot/gpt-3.5-turbo": { "litellm_provider": "github_copilot", "max_input_tokens": 16384, @@ -20627,11 +31141,14 @@ "supports_vision": true }, "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -20682,11 +31199,14 @@ "supports_vision": true }, "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.4e-05, "supported_endpoints": [ "/v1/responses" ], @@ -20745,6 +31265,86 @@ "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-5.5": { + "litellm_provider": "chatgpt", + "source": "https://platform.openai.com/docs/models/gpt-5.5", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "chatgpt/gpt-5.6-luna": { + "litellm_provider": "chatgpt", + "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-5.6-sol": { + "litellm_provider": "chatgpt", + "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-5.6-terra": { + "litellm_provider": "chatgpt", + "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true + }, "chatgpt/gpt-5.4": { "litellm_provider": "chatgpt", "max_input_tokens": 1050000, @@ -20758,7 +31358,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.4-pro": { "litellm_provider": "chatgpt", @@ -20772,7 +31377,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex": { "litellm_provider": "chatgpt", @@ -20786,7 +31395,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_minimal_reasoning_effort": true }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", @@ -20830,7 +31443,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", @@ -20844,7 +31458,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2": { "litellm_provider": "chatgpt", @@ -20859,7 +31474,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.1-codex-max": { "litellm_provider": "chatgpt", @@ -20873,7 +31493,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.1-codex-mini": { "litellm_provider": "chatgpt", @@ -20887,9 +31508,10 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, - "gigachat/GigaChat-2-Lite": { + "gigachat/GigaChat-2": { "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 128000, @@ -20951,6 +31573,15 @@ "output_cost_per_token": 0.0, "output_vector_size": 2560 }, + "gigachat/GigaEmbeddings-3B-2025-09": { + "input_cost_per_token": 0.0, + "litellm_provider": "gigachat", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, "gmi/anthropic/claude-opus-4.5": { "input_cost_per_token": 5e-06, "litellm_provider": "gmi", @@ -21068,17 +31699,6 @@ "output_cost_per_token": 8.8e-07, "supports_function_calling": true }, - "gmi/google/gemini-3-pro-preview": { - "input_cost_per_token": 2e-06, - "litellm_provider": "gmi", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_function_calling": true, - "supports_vision": true - }, "gmi/google/gemini-3-flash-preview": { "input_cost_per_token": 5e-07, "litellm_provider": "gmi", @@ -21088,7 +31708,8 @@ "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, - "supports_vision": true + "supports_vision": true, + "supports_system_messages": true }, "gmi/moonshotai/Kimi-K2-Thinking": { "input_cost_per_token": 8e-07, @@ -21127,10 +31748,21 @@ "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 2.2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, "baseten/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, @@ -21157,10 +31789,21 @@ "output_cost_per_token": 2.5e-06 }, "baseten/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, "litellm_provider": "baseten", + "max_input_tokens": 128072, + "max_output_tokens": 128072, + "max_tokens": 128072, "mode": "chat", - "output_cost_per_token": 5e-07 + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { "input_cost_per_token": 5e-07, @@ -21197,10 +31840,14 @@ "input_cost_per_token": 9e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, @@ -21208,10 +31855,14 @@ "input_cost_per_token": 2.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, @@ -21219,10 +31870,13 @@ "input_cost_per_token": 4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true }, @@ -21242,6 +31896,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -21263,11 +31918,15 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-14", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -21294,7 +31953,8 @@ "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -21302,12 +31962,13 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -21319,7 +31980,9 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5e-07, + "output_cost_per_token_batches": 2.5e-06 }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -21335,10 +31998,12 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_video_input": true, "supports_vision": true }, "gpt-3.5-turbo": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -21346,19 +32011,24 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-3.5-turbo-0125": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -21368,12 +32038,15 @@ "gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -21381,6 +32054,7 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-16k": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-06, "litellm_provider": "openai", "max_input_tokens": 16385, @@ -21393,13 +32067,15 @@ "supports_tool_choice": true }, "gpt-3.5-turbo-instruct": { + "deprecation_date": "2026-09-28", "input_cost_per_token": 1.5e-06, "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2e-06, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-3.5-turbo-instruct-0914": { "input_cost_per_token": 1.5e-06, @@ -21411,6 +32087,7 @@ "output_cost_per_token": 2e-06 }, "gpt-4": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-05, "litellm_provider": "openai", "max_input_tokens": 8192, @@ -21423,49 +32100,25 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0125-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 3e-05, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4-0613": { - "deprecation_date": "2025-06-06", + "deprecation_date": "2026-10-23", "input_cost_per_token": 3e-05, + "input_cost_per_token_batches": 1.5e-05, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true }, "gpt-4-1106-preview": { - "deprecation_date": "2026-03-26", + "deprecation_date": "2026-10-23", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -21480,6 +32133,7 @@ "supports_tool_choice": true }, "gpt-4-turbo": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 1e-05, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -21496,13 +32150,17 @@ "supports_vision": true }, "gpt-4-turbo-2024-04-09": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21511,21 +32169,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-preview": { - "input_cost_per_token": 1e-05, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 3e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4.1": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, @@ -21540,6 +32183,12 @@ "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21565,7 +32214,9 @@ }, "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 1047576, @@ -21573,7 +32224,14 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_priority": 1.4e-05, "output_cost_per_token_batches": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21611,6 +32269,12 @@ "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, "output_cost_per_token_priority": 2.8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21636,7 +32300,9 @@ }, "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, + "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, "litellm_provider": "openai", "max_input_tokens": 1047576, @@ -21644,7 +32310,14 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "output_cost_per_token_priority": 2.8e-06, "output_cost_per_token_batches": 8e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21671,6 +32344,7 @@ "gpt-4.1-nano": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_priority": 5e-08, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_priority": 2e-07, @@ -21682,6 +32356,7 @@ "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, "output_cost_per_token_priority": 8e-07, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21706,7 +32381,10 @@ }, "gpt-4.1-nano-2025-04-14": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 5e-08, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1e-07, + "input_cost_per_token_priority": 2e-07, "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 1047576, @@ -21714,7 +32392,9 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_priority": 8e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21751,6 +32431,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_priority": 1.7e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21761,6 +32442,7 @@ "supports_vision": true }, "gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 5e-06, "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_priority": 8.75e-06, @@ -21772,6 +32454,7 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, "output_cost_per_token_priority": 2.625e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21782,7 +32465,9 @@ }, "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_priority": 2.125e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -21790,7 +32475,9 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21802,7 +32489,9 @@ }, "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_priority": 2.125e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -21810,7 +32499,9 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_priority": 1.7e-05, "output_cost_per_token_batches": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21820,24 +32511,8 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-audio-preview": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-audio-preview-2024-12-17": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -21855,6 +32530,7 @@ "supports_tool_choice": true }, "gpt-4o-audio-preview-2025-06-03": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -21872,6 +32548,7 @@ "supports_tool_choice": true }, "gpt-audio": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -21881,6 +32558,7 @@ "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -21917,6 +32595,7 @@ "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions" ], @@ -21941,6 +32620,7 @@ "supports_vision": false }, "gpt-audio-2025-08-28": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "openai", @@ -21950,6 +32630,7 @@ "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -21977,6 +32658,7 @@ "supports_vision": false }, "gpt-audio-mini": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", @@ -21986,42 +32668,7 @@ "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false - }, - "gpt-audio-mini-2025-10-06": { - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -22082,7 +32729,9 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2027-01-20", + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -22105,11 +32754,19 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.25e-07, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -22117,12 +32774,14 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_priority": 1e-06, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.03, + "search_context_size_high": 0.025, "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275 + "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -22132,24 +32791,8 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-mini-audio-preview": { - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 6e-07, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-audio-preview-2024-12-17": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 1.5e-07, "litellm_provider": "openai", @@ -22166,28 +32809,10 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4o-mini-realtime-preview": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_audio_token": 1e-05, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-realtime-preview-2024-12-17": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, "litellm_provider": "openai", @@ -22216,9 +32841,9 @@ "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, "search_context_cost_per_query": { - "search_context_size_high": 0.03, + "search_context_size_high": 0.025, "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275 + "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -22230,26 +32855,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-mini-search-preview-2025-03-11": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.5e-07, - "input_cost_per_token_batches": 7.5e-08, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_batches": 3e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -22260,15 +32865,19 @@ "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/audio/transcriptions" - ] + ], + "deprecation_date": "2027-02-26", + "input_cost_per_second": 5e-05, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-tts": { - "input_cost_per_token": 2.5e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -22280,59 +32889,25 @@ "audio" ] }, - "gpt-4o-realtime-preview": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, + "gpt-4o-mini-tts-2025-03-20": { + "deprecation_date": "2027-01-06", + "input_cost_per_token": 6e-07, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2024-12-17": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2025-06-03": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 5e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 2e-05, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, @@ -22346,9 +32921,9 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { - "search_context_size_high": 0.05, - "search_context_size_low": 0.03, - "search_context_size_medium": 0.035 + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 }, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -22360,26 +32935,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-search-preview-2025-03-11": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_batches": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_batches": 5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -22390,16 +32945,26 @@ "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/audio/transcriptions" - ] + ], + "deprecation_date": "2027-02-26", + "input_cost_per_second": 0.0001, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.3e-07, + "deprecation_date": "2026-12-01", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations" ], @@ -22407,13 +32972,20 @@ "supports_pdf_input": true }, "gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.3e-07, + "deprecation_date": "2026-12-01", "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations" ], @@ -22421,13 +32993,17 @@ "supports_pdf_input": true }, "gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -22436,13 +33012,14 @@ "supports_pdf_input": true }, "gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-06, "output_cost_per_image_token": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -22450,7 +33027,78 @@ "supports_vision": true, "supports_pdf_input": true }, + "gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "gpt-image-2.5-flare-2026-09-08": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "input_cost_per_image_token": 8e-06, + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "gpt-image-2.5-sunburst-2026-09-08": { + "cache_read_input_image_token_cost": 2e-06, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "image_generation", + "input_cost_per_image_token": 8e-06, + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true, + "source": "https://developers.openai.com/api/docs/pricing" + }, "low/1024-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -22462,6 +33110,7 @@ "supports_pdf_input": true }, "low/1024-x-1536/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22473,6 +33122,7 @@ "supports_pdf_input": true }, "low/1536-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22484,6 +33134,7 @@ "supports_pdf_input": true }, "medium/1024-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.034, "litellm_provider": "openai", "mode": "image_generation", @@ -22495,6 +33146,7 @@ "supports_pdf_input": true }, "medium/1024-x-1536/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -22506,6 +33158,7 @@ "supports_pdf_input": true }, "medium/1536-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.05, "litellm_provider": "openai", "mode": "image_generation", @@ -22517,6 +33170,7 @@ "supports_pdf_input": true }, "high/1024-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.133, "litellm_provider": "openai", "mode": "image_generation", @@ -22528,6 +33182,7 @@ "supports_pdf_input": true }, "high/1024-x-1536/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -22539,6 +33194,7 @@ "supports_pdf_input": true }, "high/1536-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.2, "litellm_provider": "openai", "mode": "image_generation", @@ -22550,6 +33206,7 @@ "supports_pdf_input": true }, "standard/1024-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -22561,6 +33218,7 @@ "supports_pdf_input": true }, "standard/1024-x-1536/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22572,6 +33230,7 @@ "supports_pdf_input": true }, "standard/1536-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22583,6 +33242,7 @@ "supports_pdf_input": true }, "1024-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.009, "litellm_provider": "openai", "mode": "image_generation", @@ -22594,6 +33254,7 @@ "supports_pdf_input": true }, "1024-x-1536/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22605,6 +33266,7 @@ "supports_pdf_input": true }, "1536-x-1024/gpt-image-1.5": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.013, "litellm_provider": "openai", "mode": "image_generation", @@ -22624,7 +33286,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "low/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22635,7 +33298,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "low/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22646,7 +33310,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "medium/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.034, @@ -22657,7 +33322,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "medium/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -22668,7 +33334,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "medium/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.05, @@ -22679,7 +33346,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "high/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.133, @@ -22690,7 +33358,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "high/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -22701,7 +33370,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "high/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.2, @@ -22712,7 +33382,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "standard/1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -22723,7 +33394,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "standard/1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22734,7 +33406,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "standard/1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22745,7 +33418,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "1024-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.009, @@ -22756,7 +33430,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "1024-x-1536/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22767,7 +33442,8 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "1536-x-1024/gpt-image-1.5-2025-12-16": { "input_cost_per_image": 0.013, @@ -22778,13 +33454,16 @@ "/v1/images/edits" ], "supports_vision": true, - "supports_pdf_input": true + "supports_pdf_input": true, + "deprecation_date": "2026-12-01" }, "gpt-5": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", @@ -22793,8 +33472,15 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22822,8 +33508,42 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, + "gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-07-23", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_priority": 2.5e-06, @@ -22834,6 +33554,11 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -22858,23 +33583,28 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, - "gpt-5.1-2025-11-13": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, + "gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2026-07-23", + "input_cost_per_token": 2.5e-07, "litellm_provider": "openai", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, + "mode": "responses", + "output_cost_per_token": 2e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "supported_endpoints": [ - "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -22882,8 +33612,38 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-07-23", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -22892,26 +33652,93 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_web_search": true + }, + "gpt-5.1-codex": { + "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-07-23", + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-07-23", "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5.1-2025-11-13": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_priority": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -22924,23 +33751,31 @@ "text", "image" ], - "supports_function_calling": false, + "supports_function_calling": true, "supports_native_streaming": true, - "supports_parallel_function_calling": false, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, + "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_batches": 8.75e-08, + "cache_read_input_token_cost_flex": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, @@ -22951,6 +33786,11 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -22976,24 +33816,27 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_flex": 8.75e-07, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_flex": 7e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, - "gpt-5.2-2025-12-11": { + "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, + "deprecation_date": "2026-07-23", "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -23001,8 +33844,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -23011,26 +33853,21 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_web_search": true }, "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, + "deprecation_date": "2026-08-10", "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -23046,31 +33883,34 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_vision": true }, - "gpt-5.3-chat-latest": { + "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_batches": 8.75e-08, + "cache_read_input_token_cost_flex": 8.75e-08, "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -23078,7 +33918,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -23091,18 +33932,32 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_flex": 8.75e-07, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_flex": 7e-06, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -23131,12 +33986,20 @@ }, "gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -23163,32 +34026,287 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, - "gpt-5.6": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_flex": 3.125e-06, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_flex": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-05, + "cache_creation_input_token_cost_flex": 6.25e-06, + "cache_creation_input_token_cost_priority": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-06, + "cache_read_input_token_cost_batches": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, + "cache_read_input_token_cost_flex": 5e-07, + "cache_read_input_token_cost_priority": 2e-06, + "cache_read_input_token_cost_ultrafast": 6e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 4e-05, + "input_cost_per_token_batches": 5e-06, + "input_cost_per_token_above_272k_tokens_batches": 1e-05, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, + "input_cost_per_token_flex": 5e-06, + "input_cost_per_token_priority": 2e-05, + "input_cost_per_token_ultrafast": 6e-05, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_flex": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, + "output_cost_per_token_above_272k_tokens_priority": 0.00015, + "output_cost_per_token_batches": 2.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 3.75e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, + "output_cost_per_token_flex": 2.5e-05, + "output_cost_per_token_priority": 0.0001, + "output_cost_per_token_ultrafast": 0.0003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, + "cache_creation_input_token_cost_flex": 6.25e-08, + "cache_creation_input_token_cost_priority": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, + "cache_read_input_token_cost_batches": 5e-09, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-08, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-07, + "cache_read_input_token_cost_flex": 5e-09, + "cache_read_input_token_cost_priority": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens_flex": 1e-07, + "input_cost_per_token_above_272k_tokens_priority": 4e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_above_272k_tokens_batches": 1e-07, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, + "output_cost_per_token_above_272k_tokens_priority": 1.5e-06, + "output_cost_per_token_batches": 2.5e-07, + "output_cost_per_token_above_272k_tokens_batches": 3.75e-07, + "output_cost_per_token_flex": 2.5e-07, + "output_cost_per_token_priority": 1e-06, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.6": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06, + "cache_read_input_token_cost_flex": 2e-07, + "cache_read_input_token_cost_priority": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_batches": 4e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 8e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 4e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23207,6 +34325,7 @@ "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -23217,31 +34336,51 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_flex": 3.125e-06, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_flex": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_batches": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06, + "cache_read_input_token_cost_flex": 2e-07, + "cache_read_input_token_cost_priority": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_batches": 4e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_flex": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_above_272k_tokens_batches": 1.5e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23254,12 +34393,14 @@ "supported_output_modalities": [ "text" ], + "supports_computer_use": true, "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -23270,31 +34411,51 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-terra": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.25e-06, - "cache_creation_input_token_cost_flex": 1.5625e-06, - "cache_creation_input_token_cost_priority": 6.25e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost_flex": 1.25e-07, - "cache_read_input_token_cost_priority": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "input_cost_per_token_batches": 1.25e-06, - "input_cost_per_token_flex": 1.25e-06, - "input_cost_per_token_priority": 5e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "output_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_flex": 7.5e-06, - "output_cost_per_token_priority": 3e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_above_272k_tokens_batches": 9e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23313,6 +34474,7 @@ "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -23323,31 +34485,51 @@ "supports_xhigh_reasoning_effort": true }, "gpt-5.6-luna": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_creation_input_token_cost_flex": 6.25e-07, - "cache_creation_input_token_cost_priority": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "input_cost_per_token_batches": 5e-07, - "input_cost_per_token_flex": 5e-07, - "input_cost_per_token_priority": 2e-06, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_batches": 1e-08, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-08, + "cache_creation_input_token_cost_batches": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_flex": 1e-08, + "cache_read_input_token_cost_priority": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_above_272k_tokens_batches": 2e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "output_cost_per_token_batches": 3e-06, - "output_cost_per_token_flex": 3e-06, - "output_cost_per_token_priority": 1.2e-05, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_above_272k_tokens_batches": 9e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.4e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23366,6 +34548,7 @@ "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, @@ -23375,16 +34558,248 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-5.6-cyber": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "gpt-daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-blue-latest": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "gpt-daybreak-blue-latest": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "chat-latest": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_batches": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23394,9 +34809,15 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23422,18 +34843,25 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_batches": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, "cache_read_input_token_cost_flex": 2.5e-07, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_flex": 2.5e-06, "input_cost_per_token_batches": 2.5e-06, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23443,9 +34871,15 @@ "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_flex": 1.5e-05, "output_cost_per_token_batches": 1.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05, + "output_cost_per_token_priority": 7.5e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23471,15 +34905,18 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "output_cost_per_token_above_272k_tokens_flex": 2.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-pro": { - "cache_read_input_token_cost": 3e-06, - "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23489,8 +34926,15 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -23519,12 +34963,11 @@ "supports_low_reasoning_effort": false }, "gpt-5.5-pro-2026-04-23": { - "cache_read_input_token_cost": 3e-06, - "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23534,8 +34977,15 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -23566,12 +35016,15 @@ "gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_flex": 1.3e-07, "cache_read_input_token_cost_priority": 5e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_flex": 1.25e-06, "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "input_cost_per_token_priority": 5e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, @@ -23582,6 +35035,7 @@ "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, @@ -23608,18 +35062,26 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, "cache_read_input_token_cost_flex": 1.3e-07, "cache_read_input_token_cost_priority": 5e-07, "input_cost_per_token": 2.5e-06, "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_flex": 1.25e-06, "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, "input_cost_per_token_priority": 5e-06, "litellm_provider": "openai", "max_input_tokens": 1050000, @@ -23630,6 +35092,7 @@ "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_flex": 7.5e-06, "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05, "output_cost_per_token_priority": 3e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, @@ -23654,15 +35117,22 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro": { - "cache_read_input_token_cost": 3e-06, - "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23672,8 +35142,14 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -23698,15 +35174,17 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro-2026-03-05": { - "cache_read_input_token_cost": 3e-06, - "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -23716,8 +35194,14 @@ "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -23742,10 +35226,14 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-mini": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -23753,7 +35241,7 @@ "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -23763,6 +35251,11 @@ "output_cost_per_token_priority": 9e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23787,11 +35280,14 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, @@ -23799,7 +35295,7 @@ "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_priority": 1.5e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -23809,6 +35305,11 @@ "output_cost_per_token_priority": 9e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23833,17 +35334,20 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-nano": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -23852,6 +35356,11 @@ "output_cost_per_token_batches": 6.25e-07, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23876,17 +35385,21 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_batches": 1e-08, "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "input_cost_per_token_flex": 1e-07, "input_cost_per_token_batches": 1e-07, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -23895,6 +35408,11 @@ "output_cost_per_token_batches": 6.25e-07, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -23919,6 +35437,8 @@ "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, @@ -23927,11 +35447,17 @@ "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -23959,15 +35485,22 @@ "supports_minimal_reasoning_effort": true }, "gpt-5-pro-2025-10-06": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.5e-05, "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 272000, + "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -23996,9 +35529,12 @@ }, "gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, "cache_read_input_token_cost_flex": 6.25e-08, "cache_read_input_token_cost_priority": 2.5e-07, + "deprecation_date": "2026-12-11", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", @@ -24007,8 +35543,15 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24038,6 +35581,7 @@ }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-07-23", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -24073,6 +35617,7 @@ }, "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-07-23", "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -24080,42 +35625,9 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ @@ -24129,161 +35641,11 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_priority": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_priority": 2.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "output_cost_per_token_priority": 2e-05, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-codex-mini": { - "cache_read_input_token_cost": 2.5e-08, - "cache_read_input_token_cost_priority": 4.5e-08, - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_priority": 4.5e-07, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 2e-06, - "output_cost_per_token_priority": 3.6e-06, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "cache_read_input_token_cost_priority": 3.5e-07, - "input_cost_per_token": 1.75e-06, - "input_cost_per_token_priority": 3.5e-06, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "output_cost_per_token": 1.4e-05, - "output_cost_per_token_priority": 2.8e-05, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_vision": true }, "gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, @@ -24297,6 +35659,12 @@ "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ], @@ -24320,13 +35688,48 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "deprecation_date": "2027-04-01" + }, + "gpt-5.3-chat-latest": { + "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2026-08-10", + "input_cost_per_token": 1.75e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", @@ -24335,8 +35738,15 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24366,9 +35776,12 @@ }, "gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-12-11", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "openai", @@ -24377,8 +35790,15 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, "output_cost_per_token_flex": 1e-06, "output_cost_per_token_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24408,8 +35828,10 @@ }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "input_cost_per_token_flex": 2.5e-08, "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "openai", @@ -24418,7 +35840,14 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24448,8 +35877,12 @@ }, "gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_batches": 2.5e-09, "cache_read_input_token_cost_flex": 2.5e-09, + "deprecation_date": "2026-12-11", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, + "input_cost_per_token_priority": 2.5e-06, "input_cost_per_token_flex": 2.5e-08, "litellm_provider": "openai", "max_input_tokens": 272000, @@ -24457,7 +35890,14 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, "output_cost_per_token_flex": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -24486,24 +35926,36 @@ "supports_minimal_reasoning_effort": true }, "gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.3e-07, + "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, + "input_cost_per_image_token_batches": 5e-06, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "deprecation_date": "2026-12-01", "input_cost_per_image_token": 2.5e-06, + "input_cost_per_image_token_batches": 1.25e-06, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -24511,9 +35963,12 @@ }, "gpt-realtime": { "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -24522,6 +35977,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24543,9 +35999,11 @@ }, "gpt-realtime-1.5": { "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -24554,6 +36012,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24575,17 +36034,20 @@ }, "gpt-realtime-2": { "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24608,9 +36070,10 @@ "gpt-realtime-2.1": { "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -24621,6 +36084,7 @@ "output_cost_per_token": 2.4e-05, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24643,19 +36107,21 @@ "gpt-realtime-2.1-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24678,15 +36144,20 @@ "gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_image_token_cost": 8e-08, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", - "max_input_tokens": 128000, + "max_input_tokens": 32000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -24708,9 +36179,12 @@ }, "gpt-realtime-2025-08-28": { "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_image_token_cost": 5e-07, "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -24719,6 +36193,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -25054,99 +36529,50 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/llama-3.1-8b-instant": { - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/gemma-7b-it": { - "input_cost_per_token": 5e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/meta-llama/llama-guard-4-12b": { + "groq/llama-guard-3-8b": { + "deprecation_date": "2025-06-06", "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, - "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2e-07 + "output_cost_per_token": 2e-07, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "input_cost_per_token": 2e-07, + "groq/meta-llama/llama-prompt-guard-2-22m": { + "input_cost_per_token": 3e-08, "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 512, + "max_output_tokens": 512, + "max_tokens": 512, "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 3e-08, + "source": "https://console.groq.com/docs/models" }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "input_cost_per_token": 1.1e-07, + "groq/meta-llama/llama-prompt-guard-2-86m": { + "input_cost_per_token": 4e-08, "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 512, + "max_output_tokens": 512, + "max_tokens": 512, "mode": "chat", - "output_cost_per_token": 3.4e-07, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/moonshotai/kimi-k2-instruct-0905": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "groq", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 4e-08, + "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" }, "groq/openai/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "groq", "max_input_tokens": 131072, - "max_output_tokens": 32766, - "max_tokens": 32766, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -25159,10 +36585,15 @@ "input_cost_per_token": 7.5e-08, "litellm_provider": "groq", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -25179,32 +36610,34 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, - "groq/playai-tts": { - "input_cost_per_character": 5e-05, + "groq/canopylabs/orpheus-v1-english": { + "input_cost_per_character": 2.2e-05, "litellm_provider": "groq", - "max_input_tokens": 10000, - "max_output_tokens": 10000, - "max_tokens": 10000, - "mode": "audio_speech" + "max_input_tokens": 4000, + "max_output_tokens": 50000, + "max_tokens": 50000, + "mode": "audio_speech", + "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, - "groq/qwen/qwen3-32b": { - "input_cost_per_token": 2.9e-07, + "groq/canopylabs/orpheus-arabic-saudi": { + "input_cost_per_character": 4e-05, "litellm_provider": "groq", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true + "max_input_tokens": 4000, + "max_output_tokens": 50000, + "max_tokens": 50000, + "mode": "audio_speech", + "source": "https://console.groq.com/docs/models" }, "groq/whisper-large-v3": { "input_cost_per_second": 3.083e-05, @@ -25218,24 +36651,6 @@ "mode": "audio_transcription", "output_cost_per_second": 0.0 }, - "hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", "max_tokens": 8192, @@ -25277,6 +36692,7 @@ "max_output_tokens": 8192 }, "high/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.167, "input_cost_per_pixel": 1.59263611e-07, "litellm_provider": "openai", @@ -25287,6 +36703,7 @@ ] }, "high/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -25297,6 +36714,7 @@ ] }, "high/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.25, "input_cost_per_pixel": 1.58945719e-07, "litellm_provider": "openai", @@ -25632,13 +37050,14 @@ "supports_tool_choice": true }, "jina-reranker-v2-base-multilingual": { - "input_cost_per_token": 1.8e-08, + "input_cost_per_token": 5e-08, "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, "max_tokens": 1024, "mode": "rerank", - "output_cost_per_token": 1.8e-08 + "output_cost_per_token": 0.0, + "source": "https://api.jina.ai/v1/models" }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -25651,6 +37070,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -25672,7 +37092,10 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.65e-06, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -25680,12 +37103,13 @@ "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -25697,7 +37121,9 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-07, + "output_cost_per_token_batches": 2.75e-06 }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -25806,6 +37232,22 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inception", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://docs.inceptionlabs.ai/get-started/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "text-completion-inception/mercury-edit-2": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, @@ -26082,6 +37524,7 @@ "supports_tool_choice": true }, "low/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.011, "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "openai", @@ -26092,6 +37535,7 @@ ] }, "low/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", @@ -26102,6 +37546,7 @@ ] }, "low/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.016, "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "openai", @@ -26126,6 +37571,7 @@ "output_cost_per_image": 0.072 }, "medium/1024-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.042, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -26136,6 +37582,7 @@ ] }, "medium/1024-x-1536/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -26146,6 +37593,7 @@ ] }, "medium/1536-x-1024/gpt-image-1": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.063, "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "openai", @@ -26156,6 +37604,7 @@ ] }, "low/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.005, "litellm_provider": "openai", "mode": "image_generation", @@ -26164,6 +37613,7 @@ ] }, "low/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", @@ -26172,6 +37622,7 @@ ] }, "low/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.006, "litellm_provider": "openai", "mode": "image_generation", @@ -26180,6 +37631,7 @@ ] }, "medium/1024-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.011, "litellm_provider": "openai", "mode": "image_generation", @@ -26188,6 +37640,7 @@ ] }, "medium/1024-x-1536/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", @@ -26196,6 +37649,7 @@ ] }, "medium/1536-x-1024/gpt-image-1-mini": { + "deprecation_date": "2026-12-01", "input_cost_per_image": 0.015, "litellm_provider": "openai", "mode": "image_generation", @@ -26232,7 +37686,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1e-06 + "output_cost_per_token": 1e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama2-70b-chat-v1": { "input_cost_per_token": 1.95e-06, @@ -26241,27 +37696,30 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2.56e-06 + "output_cost_per_token": 2.56e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 9.9e-07, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, @@ -26277,13 +37735,14 @@ "supports_tool_choice": false }, "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -26311,13 +37770,14 @@ "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -26402,7 +37862,12 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, - "source": "https://dev.meta.ai/docs/getting-started/pricing-rate-limits", + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -26429,13 +37894,193 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "meta/muse-spark-1.2": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "meta/muse-spark-1.2-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "meta/muse-spark-1.3": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "meta/muse-spark-1.3-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "meta/muse-voice-transcribe-1.0": { + "input_cost_per_second": 0.00005, + "litellm_provider": "meta", + "mode": "audio_transcription", + "source": "https://dev.meta.ai/docs/speech-to-text", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", + "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text" ], @@ -26451,7 +38096,7 @@ "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", + "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text" ], @@ -26467,7 +38112,7 @@ "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", + "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" @@ -26484,7 +38129,7 @@ "max_output_tokens": 4028, "max_tokens": 4028, "mode": "chat", - "source": "https://llama.developer.meta.com/docs/models", + "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" @@ -26498,39 +38143,50 @@ "minimax.minimax-m2": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "minimax.minimax-m2.1": { "input_cost_per_token": 3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 196000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "minimax/speech-02-hd": { "input_cost_per_character": 0.0001, @@ -26661,62 +38317,81 @@ "input_cost_per_token": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, - "supports_system_messages": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-07, @@ -26726,49 +38401,59 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { - "input_cost_per_token": 8e-06, + "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 1.2e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { - "input_cost_per_token": 3e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 9e-06, + "output_cost_per_token": 6e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": true }, "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.mistral-small-2402-v1:0": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true }, "mistral.mixtral-8x7b-instruct-v0:1": { @@ -26779,6 +38464,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_tool_choice": true }, "mistral.voxtral-mini-3b-2507": { @@ -26789,6 +38475,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true @@ -26801,49 +38488,43 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, - "mistral/codestral-2405": { - "input_cost_per_token": 1e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 3e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/codestral-2508": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://mistral.ai/news/codestral-25-08", + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-latest": { - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, + "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-mamba-latest": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -26855,63 +38536,8 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "mistral/devstral-medium-2507": { - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2505": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2507": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-small-latest": { - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/labs-devstral-small-2512": { + "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -26926,6 +38552,7 @@ "supports_tool_choice": true }, "mistral/devstral-latest": { + "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -26940,6 +38567,7 @@ "supports_tool_choice": true }, "mistral/devstral-medium-latest": { + "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -26953,61 +38581,276 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/devstral-2512": { - "input_cost_per_token": 4e-07, + "mistral/ministral-14b-2512": { + "input_cost_per_token": 2e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 }, - "mistral/magistral-medium-2506": { - "input_cost_per_token": 2e-06, + "mistral/ministral-14b-latest": { + "input_cost_per_token": 2e-07, "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 2e-08 + }, + "mistral/ministral-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 + }, + "mistral/ministral-3b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1e-08 + }, + "mistral/mistral-embed-2312": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "source": "https://docs.mistral.ai/models/mistral-embed-23-12" + }, + "mistral/mistral-medium-3": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/voxtral-mini-transcribe-realtime-latest": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-tts-latest": { + "input_cost_per_character": 1.6e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, + "mistral/voxtral-small-2507": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/magistral-medium-2509": { - "input_cost_per_token": 2e-06, + "mistral/voxtral-small-latest": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "deprecation_date": "2026-10-31", + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/magistral-medium-1-2-2509": { - "input_cost_per_token": 2e-06, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-2", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true @@ -27015,102 +38858,89 @@ "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, "mode": "ocr", "supported_endpoints": [ - "/v1/ocr" + "/v1/ocr", + "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4-0": { + "deprecation_date": "2026-09-30", "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, "mode": "ocr", "supported_endpoints": [ - "/v1/ocr" + "/v1/ocr", + "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, - "mistral/mistral-ocr-2505-completion": { + "mistral/mistral-ocr-4-1": { + "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, "litellm_provider": "mistral", - "ocr_cost_per_page": 0.001, - "annotation_cost_per_page": 0.003, "mode": "ocr", + "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, + "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", "supported_endpoints": [ - "/v1/ocr" - ], - "source": "https://mistral.ai/pricing#api-pricing" + "/v1/ocr", + "/v1/batch" + ] }, "mistral/mistral-ocr-2512": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.002, + "ocr_cost_per_page_batches": 0.001, "annotation_cost_per_page": 0.003, + "annotation_cost_per_page_batches": 0.0015, "mode": "ocr", "supported_endpoints": [ - "/v1/ocr" + "/v1/ocr", + "/v1/batch" ], "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/magistral-medium-latest": { - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://mistral.ai/news/magistral", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-small-2506": { - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "mistral/magistral-small-latest": { - "input_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", + "output_cost_per_token": 6e-07, + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-small-1-2-2509": { - "input_cost_per_token": 5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, @@ -27120,6 +38950,7 @@ "mode": "embedding" }, "mistral/codestral-embed": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, @@ -27127,52 +38958,15 @@ "mode": "embedding" }, "mistral/codestral-embed-2505": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, "max_tokens": 8192, "mode": "embedding" }, - "mistral/mistral-large-2402": { - "input_cost_per_token": 4e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2407": { - "input_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2411": { - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-large-latest": { + "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27188,6 +38982,7 @@ "supports_vision": true }, "mistral/mistral-large-3": { + "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27203,6 +38998,7 @@ "supports_vision": true }, "mistral/mistral-large-2512": { + "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27218,58 +39014,7 @@ "supports_vision": true }, "mistral/mistral-medium": { - "input_cost_per_token": 2.7e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 8.1e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2312": { - "input_cost_per_token": 2.7e-06, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 8.1e-06, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2505": { - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2508": { - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/mistral-medium-2604": { + "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27277,6 +39022,31 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-medium-2604": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -27286,6 +39056,7 @@ "supports_vision": true }, "mistral/mistral-medium-latest": { + "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27293,6 +39064,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -27301,22 +39076,8 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-3-1-2508": { - "input_cost_per_token": 4e-07, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-3-5": { + "cache_read_input_token_cost": 1.5e-07, "input_cost_per_token": 1.5e-06, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27324,6 +39085,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -27333,6 +39098,7 @@ "supports_vision": true }, "mistral/mistral-small": { + "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -27346,36 +39112,28 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "input_cost_per_token": 6e-08, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/mistral-small-3-2-2506": { - "input_cost_per_token": 6e-08, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", + "output_cost_per_token": 6e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "mistral/ministral-3-3b-2512": { + "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, @@ -27391,6 +39149,7 @@ "supports_vision": true }, "mistral/ministral-3-8b-2512": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27406,6 +39165,7 @@ "supports_vision": true }, "mistral/ministral-3-14b-2512": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27421,6 +39181,7 @@ "supports_vision": true }, "mistral/ministral-8b-2512": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27436,6 +39197,7 @@ "supports_vision": true }, "mistral/ministral-8b-latest": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -27451,30 +39213,7 @@ "supports_vision": true }, "mistral/mistral-tiny": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-codestral-mamba": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-7b": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -27487,6 +39226,7 @@ "supports_tool_choice": true }, "mistral/open-mistral-nemo": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -27499,74 +39239,8 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-mistral-nemo-2407": { - "input_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x22b": { - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x7b": { - "input_cost_per_token": 7e-07, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/pixtral-12b-2409": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/pixtral-large-2411": { - "input_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/pixtral-large-latest": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -27583,73 +39257,53 @@ "moonshot.kimi-k2-thinking": { "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true }, - "moonshot/kimi-k2-0711-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-0905-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, + "moonshot/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_token": 4e-06, + "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-turbo-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_video_input": true, + "supports_vision": true }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-07, @@ -27685,110 +39339,27 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-latest": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, + "moonshot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-128k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-32k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-latest-8k": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-thinking-preview": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2025-11-11", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_vision": true - }, - "moonshot/kimi-k2-thinking": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-thinking-turbo": { - "cache_read_input_token_cost": 1.5e-07, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 1.15e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_video_input": true, + "supports_vision": true }, "moonshot/moonshot-v1-128k": { "input_cost_per_token": 2e-06, @@ -27803,19 +39374,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-128k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-128k-vision-preview": { "input_cost_per_token": 2e-06, "litellm_provider": "moonshot", @@ -27843,19 +39401,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-32k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 1e-06, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-32k-vision-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "moonshot", @@ -27883,19 +39428,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-07, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-8k-vision-preview": { "input_cost_per_token": 2e-07, "litellm_provider": "moonshot", @@ -27975,6 +39507,7 @@ ] }, "multimodalembedding@001": { + "deprecation_date": "2027-04-01", "input_cost_per_character": 2e-07, "input_cost_per_image": 0.0001, "input_cost_per_token": 8e-07, @@ -28152,7 +39685,7 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-0528": { "max_tokens": 164000, @@ -28164,7 +39697,7 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_tokens": 128000, @@ -28175,7 +39708,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3": { "max_tokens": 128000, @@ -28186,7 +39719,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 128000, @@ -28197,30 +39730,30 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, + "max_tokens": 110000, + "max_input_tokens": 110000, + "max_output_tokens": 110000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 4e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/meta-llama/Llama-Guard-3-8B": { "max_tokens": 128000, @@ -28230,7 +39763,7 @@ "output_cost_per_token": 6e-08, "litellm_provider": "nebius", "mode": "chat", - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 128000, @@ -28241,7 +39774,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { "max_tokens": 128000, @@ -28252,7 +39785,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { "max_tokens": 128000, @@ -28263,7 +39796,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/mistralai/Mistral-Nemo-Instruct-2407": { "max_tokens": 128000, @@ -28274,7 +39807,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 128000, @@ -28285,7 +39818,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { "max_tokens": 128000, @@ -28296,7 +39829,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { "max_tokens": 131072, @@ -28307,7 +39840,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-235B-A22B": { "max_tokens": 262144, @@ -28318,18 +39851,18 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { "max_tokens": 32768, @@ -28340,7 +39873,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-14B": { "max_tokens": 32768, @@ -28351,7 +39884,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-4B": { "max_tokens": 32768, @@ -28362,7 +39895,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/QwQ-32B": { "max_tokens": 32768, @@ -28374,7 +39907,7 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-72B-Instruct": { "max_tokens": 128000, @@ -28385,7 +39918,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-32B-Instruct": { "max_tokens": 128000, @@ -28396,7 +39929,7 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-Coder-7B": { "max_tokens": 32768, @@ -28407,19 +39940,19 @@ "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 4e-07, + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, "litellm_provider": "nebius", "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { "max_tokens": 131072, @@ -28431,7 +39964,7 @@ "mode": "chat", "supports_function_calling": true, "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2-VL-7B-Instruct": { "max_tokens": 131072, @@ -28442,7 +39975,366 @@ "litellm_provider": "nebius", "mode": "chat", "supports_vision": true, - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" + }, + "nebius/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" + }, + "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" + }, + "nebius/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 3.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" + }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "max_input_tokens": 979000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "nebius/MiniMaxAI/MiniMax-M2.5": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" + }, + "nebius/MiniMaxAI/MiniMax-M3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" + }, + "nebius/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" + }, + "nebius/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" + }, + "nebius/moonshotai/Kimi-K3": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" + }, + "nebius/NousResearch/Hermes-4-405B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" + }, + "nebius/NousResearch/Hermes-4-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" + }, + "nebius/nvidia/Cosmos3-Super-Reasoner": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" + }, + "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" + }, + "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" + }, + "nebius/nvidia/Nemotron-3-Nano-Omni": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" + }, + "nebius/nvidia/nemotron-3-super-120b-a12b": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" + }, + "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" + }, + "nebius/nvidia/Nemotron-3_5-Lightning": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" + }, + "nebius/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" + }, + "nebius/openbmb/MiniCPM-V-4_5": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 6.58e-07, + "output_cost_per_token": 1.11e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" + }, + "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" + }, + "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" + }, + "nebius/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" + }, + "nebius/Qwen/Qwen3.8-27B": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B", + "supports_function_calling": true, + "supports_reasoning": true + }, + "nebius/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" + }, + "nebius/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" + }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1024000, + "max_tokens": 1024000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, + "nebius/zai-org/GLM-5.3-Flash": { + "max_tokens": 1024000, + "max_input_tokens": 1024000, + "max_output_tokens": 1024000, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash", + "supports_vision": true }, "nebius/BAAI/bge-en-icl": { "max_tokens": 32768, @@ -28451,7 +40343,7 @@ "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/BAAI/bge-multilingual-gemma2": { "max_tokens": 8192, @@ -28460,7 +40352,7 @@ "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" }, "nebius/intfloat/e5-mistral-7b-instruct": { "max_tokens": 32768, @@ -28469,16 +40361,29 @@ "output_cost_per_token": 0.0, "litellm_provider": "nebius", "mode": "embedding", - "source": "https://nebius.com/prices-ai-studio" + "source": "https://nebius.com/prices" + }, + "nebius/Qwen/Qwen3-Embedding-8B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" }, "nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, @@ -28486,49 +40391,64 @@ "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_native_structured_output": true + "supports_audio_input": false, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, "o1": { "cache_read_input_token_cost": 7.5e-06, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, @@ -28541,13 +40461,17 @@ }, "o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -28559,6 +40483,7 @@ "supports_vision": true }, "o1-pro": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", @@ -28568,6 +40493,7 @@ "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -28591,6 +40517,7 @@ "supports_vision": true }, "o1-pro-2025-03-19": { + "deprecation_date": "2026-10-23", "input_cost_per_token": 0.00015, "input_cost_per_token_batches": 7.5e-05, "litellm_provider": "openai", @@ -28600,6 +40527,7 @@ "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -28627,6 +40555,7 @@ "cache_read_input_token_cost_flex": 2.5e-07, "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "input_cost_per_token_flex": 1e-06, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", @@ -28635,40 +40564,15 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, "output_cost_per_token_flex": 4e-06, "output_cost_per_token_priority": 1.4e-05, - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o3-2025-04-16": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", @@ -28695,16 +40599,14 @@ "o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -28715,32 +40617,46 @@ "supported_output_modalities": [ "text" ], - "supports_function_calling": true, + "supports_function_calling": false, "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" }, - "o3-deep-research-2025-06-26": { - "cache_read_input_token_cost": 2.5e-06, - "input_cost_per_token": 1e-05, - "input_cost_per_token_batches": 5e-06, + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2026-12-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 4e-05, - "output_cost_per_token_batches": 2e-05, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_flex": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ + "/v1/responses", "/v1/chat/completions", - "/v1/batch", - "/v1/responses" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -28750,25 +40666,28 @@ "text" ], "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, "o3-mini": { "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -28779,13 +40698,17 @@ }, "o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -28804,6 +40727,12 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -28826,6 +40755,7 @@ "supports_web_search": true }, "o3-pro-2025-06-10": { + "deprecation_date": "2026-12-11", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "openai", @@ -28835,6 +40765,12 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" @@ -28858,9 +40794,11 @@ }, "o4-mini": { "cache_read_input_token_cost": 2.75e-07, - "cache_read_input_token_cost_flex": 1.375e-07, + "cache_read_input_token_cost_flex": 1.38e-07, "cache_read_input_token_cost_priority": 5e-07, + "deprecation_date": "2026-10-23", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "input_cost_per_token_flex": 5.5e-07, "input_cost_per_token_priority": 2e-06, "litellm_provider": "openai", @@ -28869,27 +40807,15 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, "output_cost_per_token_flex": 2.2e-06, "output_cost_per_token_priority": 8e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o4-mini-2025-04-16": { - "cache_read_input_token_cost": 2.75e-07, - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, @@ -28903,16 +40829,14 @@ "o4-mini-deep-research": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, + "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -28923,47 +40847,47 @@ "supported_output_modalities": [ "text" ], - "supports_function_calling": true, + "supports_function_calling": false, "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, "supports_vision": true, - "supports_web_search": true + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" }, - "o4-mini-deep-research-2025-06-26": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_flex": 1.38e-07, + "cache_read_input_token_cost_priority": 5e-07, + "deprecation_date": "2026-10-23", + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, + "input_cost_per_token_flex": 5.5e-07, + "input_cost_per_token_priority": 2e-06, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 8e-06, - "output_cost_per_token_batches": 4e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "output_cost_per_token_flex": 2.2e-06, + "output_cost_per_token_priority": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, + "supports_parallel_function_calling": false, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true @@ -29134,7 +41058,7 @@ "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true @@ -29147,7 +41071,7 @@ "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true @@ -29160,7 +41084,7 @@ "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true @@ -29178,7 +41102,12 @@ "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/google.gemini-2.5-pro": { "input_cost_per_token": 1.25e-06, @@ -29192,7 +41121,12 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/google.gemini-2.5-flash-lite": { "input_cost_per_token": 7.5e-08, @@ -29207,7 +41141,12 @@ "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": false, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/cohere.command-a-vision": { "input_cost_per_token": 1.56e-06, @@ -29217,7 +41156,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": true, "supports_response_schema": false, "supports_native_streaming": true, @@ -29231,7 +41170,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_function_calling": false, "supports_response_schema": false, "supports_native_streaming": true @@ -29242,7 +41181,7 @@ "max_input_tokens": 512, "mode": "embedding", "output_vector_size": 1024, - "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", "supports_vision": true }, "oci/cohere.command-a-reasoning-08-2025": { @@ -29817,6 +41756,10 @@ "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -29824,12 +41767,17 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, "input_cost_per_token": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -29837,6 +41785,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -29846,23 +41795,36 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "openrouter/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-07, + "cache_creation_input_token_cost_above_1hr": 5e-07, + "cache_read_input_token_cost": 3e-08, "input_cost_per_image": 0.0004, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", @@ -29873,7 +41835,14 @@ "supports_tool_choice": true, "supports_vision": true, "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_web_search": true }, "openrouter/anthropic/claude-3.5-sonnet": { "input_cost_per_token": 3e-06, @@ -29905,25 +41874,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "openrouter/anthropic/claude-opus-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, "openrouter/anthropic/claude-opus-4.1": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 1.875e-05, @@ -29942,11 +41892,18 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": false, + "supports_web_search": true }, "openrouter/anthropic/claude-sonnet-4": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost": 3e-07, "cache_read_input_token_cost_above_200k_tokens": 6e-07, @@ -29954,6 +41911,122 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.5": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -29965,103 +42038,23 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-sonnet-4.6": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true - }, - "openrouter/anthropic/claude-opus-4.6": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true }, "openrouter/anthropic/claude-haiku-4.5": { "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -30070,11 +42063,18 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true }, "openrouter/anthropic/claude-opus-4.7": { "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openrouter", @@ -30093,165 +42093,370 @@ "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "prompt_cache_min_tokens": 2048, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-5": { + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": false, + "supports_audio_input": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "openrouter/bytedance/ui-tars-1.5-7b": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", - "supports_tool_choice": true + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 2.574e-07, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 2.8e-07, - "supports_prompt_caching": true, - "supports_tool_choice": true + "output_cost_per_token": 1.0287e-06, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 1.4e-07, + "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 163840, + "max_output_tokens": 147456, + "max_tokens": 147456, "mode": "chat", - "output_cost_per_token": 2.8e-07, - "supports_prompt_caching": true, - "supports_tool_choice": true + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 2.5e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 8e-07, + "output_cost_per_token": 9.5e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.3e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-v3.2": { + "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-09-28", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 4.2e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-v3.2-exp": { - "input_cost_per_token": 2e-07, + "cache_read_input_token_cost": 2e-08, + "deprecation_date": "2026-09-28", + "input_cost_per_token": 2.7e-07, "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 147456, + "max_tokens": 147456, "mode": "chat", - "output_cost_per_token": 4e-07, + "output_cost_per_token": 4.1e-07, + "source": "https://openrouter.ai/api/v1/models", "supports_assistant_prefill": true, + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_tool_choice": true + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-r1": { - "input_cost_per_token": 5.5e-07, + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 7e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 2.19e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://openrouter.ai/api/v1/models", "supports_assistant_prefill": true, + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/deepseek/deepseek-r1-0528": { + "cache_read_input_token_cost": 3.5e-07, "input_cost_per_token": 5e-07, "input_cost_per_token_cache_hit": 1.4e-07, "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.15e-06, + "source": "https://openrouter.ai/api/v1/models", "supports_assistant_prefill": true, + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, + "openrouter/deepseek/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.74e-08, + "input_cost_per_token": 2.088e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 4e-07, - "supports_audio_output": true, + "output_cost_per_token": 4.176e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 3e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 7e-07, + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/fireworks/ember-1": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false }, "openrouter/google/gemini-2.5-flash": { - "input_cost_per_audio_token": 7e-07, + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 1e-07, + "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65535, + "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, - "supports_audio_output": true, + "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_image_size": false + "supports_image_size": false, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-20", + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_pdf_input": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_video_input": true }, "openrouter/google/gemini-2.5-pro": { - "input_cost_per_audio_token": 7e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 1.25e-07, + "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, - "supports_audio_output": true, + "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "deprecation_date": "2026-10-20", + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_pdf_input": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_video_input": true }, "openrouter/google/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -30295,18 +42500,20 @@ "supports_web_search": true }, "openrouter/google/gemini-3-flash-preview": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30321,6 +42528,7 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": true, "supports_audio_output": false, "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -30333,9 +42541,12 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "tpm": 800000 + "tpm": 800000, + "supports_video_input": true }, "openrouter/google/gemini-3.1-flash-lite-preview": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, @@ -30347,7 +42558,7 @@ "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "rpm": 2000, - "source": "https://ai.google.dev/pricing/gemini-3", + "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30379,6 +42590,8 @@ "tpm": 800000 }, "openrouter/google/gemini-3.1-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 5e-08, "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, @@ -30390,7 +42603,7 @@ "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -30422,9 +42635,12 @@ "tpm": 800000 }, "openrouter/google/gemini-3.1-pro-preview": { + "cache_creation_input_token_cost": 3.75e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_audio_token_cost": 2e-07, + "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "openrouter", @@ -30434,7 +42650,7 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image", @@ -30452,25 +42668,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", - "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 3686, + "max_tokens": 3686, "mode": "chat", - "output_cost_per_token": 1.875e-06, - "supports_tool_choice": true + "output_cost_per_token": 1.1e-07, + "supports_tool_choice": false, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/mancer/weaver": { - "input_cost_per_token": 5.625e-06, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", - "max_tokens": 2000, + "max_tokens": 6000, "mode": "chat", - "output_cost_per_token": 5.625e-06, - "supports_tool_choice": true, + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false, "max_input_tokens": 8000, - "max_output_tokens": 2000 + "max_output_tokens": 6000, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/meta-llama/llama-3-70b-instruct": { "input_cost_per_token": 5.9e-07, @@ -30483,87 +42721,107 @@ "max_output_tokens": 8000 }, "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 2.55e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, + "max_output_tokens": 176947, + "max_tokens": 176947, "mode": "chat", - "output_cost_per_token": 1.02e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/mistralai/devstral-2512": { + "cache_read_input_token_cost": 4e-08, "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 4e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 209715, + "max_tokens": 209715, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "supports_web_search": false }, "openrouter/mistralai/ministral-3b-2512": { + "cache_read_input_token_cost": 1e-08, "input_cost_per_image": 0, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/mistralai/ministral-8b-2512": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_image": 0, "input_cost_per_token": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/mistralai/ministral-14b-2512": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_image": 0, "input_cost_per_token": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/mistralai/mistral-large-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/mistralai/mistral-7b-instruct": { "input_cost_per_token": 1.3e-07, @@ -30576,69 +42834,142 @@ "max_output_tokens": 8191 }, "openrouter/mistralai/mistral-large": { - "input_cost_per_token": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", - "max_tokens": 8191, + "max_tokens": 102400, "mode": "chat", - "output_cost_per_token": 2.4e-05, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 8191 + "max_output_tokens": 102400, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 3.51e-07, "litellm_provider": "openrouter", - "max_tokens": 131072, + "max_tokens": 102400, "mode": "chat", - "output_cost_per_token": 3e-07, - "supports_tool_choice": true, - "max_input_tokens": 131072, - "max_output_tokens": 131072 - }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 5.55e-07, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 102400, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 9.375e-08, + "litellm_provider": "openrouter", + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true, + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false }, "openrouter/mistralai/mixtral-8x22b-instruct": { - "input_cost_per_token": 6.5e-07, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, "litellm_provider": "openrouter", - "max_tokens": 65536, + "max_tokens": 52428, "mode": "chat", - "output_cost_per_token": 6.5e-07, + "output_cost_per_token": 6e-06, "supports_tool_choice": true, "max_input_tokens": 65536, - "max_output_tokens": 65536 + "max_output_tokens": 52428, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/moonshotai/kimi-k2.5", + "output_cost_per_token": 2.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3.5-lightning": { + "cache_read_input_token_cost": 2.975e-08, + "input_cost_per_token": 5.95e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 1.5e-06, "supports_tool_choice": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/gpt-3.5-turbo-16k": { "input_cost_per_token": 3e-06, @@ -30648,7 +42979,16 @@ "output_cost_per_token": 4e-06, "supports_tool_choice": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/gpt-4": { "input_cost_per_token": 3e-05, @@ -30658,7 +42998,16 @@ "output_cost_per_token": 6e-05, "supports_tool_choice": true, "max_input_tokens": 8191, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/gpt-4.1": { "cache_read_input_token_cost": 5e-07, @@ -30669,13 +43018,18 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-4.1-mini": { "cache_read_input_token_cost": 1e-07, @@ -30686,13 +43040,18 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-4.1-nano": { "cache_read_input_token_cost": 2.5e-08, @@ -30703,26 +43062,39 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-4o": { "input_cost_per_token": 2.5e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-06, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_web_search": true }, "openrouter/openai/gpt-4o-2024-05-13": { "input_cost_per_token": 5e-06, @@ -30732,10 +43104,17 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -30779,11 +43158,12 @@ "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" @@ -30791,18 +43171,26 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5": { "cache_read_input_token_cost": 1.25e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" @@ -30810,18 +43198,26 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" @@ -30829,18 +43225,26 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5-nano": { "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" @@ -30848,8 +43252,15 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, @@ -30860,7 +43271,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" @@ -30868,27 +43279,36 @@ "supported_output_modalities": [ "text" ], + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5.2": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-07, "input_cost_per_token": 1.75e-06, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5.2-chat": { "input_cost_per_image": 0, @@ -30896,59 +43316,166 @@ "input_cost_per_token": 1.75e-06, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/gpt-5.2-pro": { "input_cost_per_image": 0, "input_cost_per_token": 2.1e-05, "litellm_provider": "openrouter", - "max_input_tokens": 272000, + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000168, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "default_reasoning_effort": "medium", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-sol-pro": { + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true }, "openrouter/openai/gpt-oss-120b": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 3.7e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/openai/gpt-oss-120b", + "output_cost_per_token": 1.7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-oss-120b:batch": { + "input_cost_per_token": 2.96e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 1.36e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/gpt-oss-20b": { - "input_cost_per_token": 2e-08, + "cache_read_input_token_cost": 9e-09, + "input_cost_per_token": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/openai/gpt-oss-20b", + "output_cost_per_token": 9e-08, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/openai/o1": { "cache_read_input_token_cost": 7.5e-06, @@ -30959,51 +43486,79 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, "openrouter/openai/o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true }, "openrouter/openai/o3-mini-high": { "input_cost_per_token": 1.1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-07, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true }, "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 1.8e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "openrouter", - "max_input_tokens": 33792, - "max_output_tokens": 33792, - "max_tokens": 33792, + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_tool_choice": true + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, "openrouter/qwen/qwen-vl-plus": { "input_cost_per_token": 2.1e-07, @@ -31017,56 +43572,100 @@ "supports_vision": true }, "openrouter/qwen/qwen3-coder": { - "input_cost_per_token": 2.2e-07, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", - "max_input_tokens": 262100, - "max_output_tokens": 262100, - "max_tokens": 262100, - "mode": "chat", - "output_cost_per_token": 9.5e-07, - "source": "https://openrouter.ai/qwen/qwen3-coder", - "supports_tool_choice": true, - "supports_function_calling": true - }, - "openrouter/qwen/qwen3-coder-plus": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 997952, + "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/qwen/qwen3-coder-plus", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_tool_choice": true, "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-coder-plus": { + "cache_creation_input_token_cost": 8.125e-07, + "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, + "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06, + "cache_read_input_token_cost": 1.3e-07, + "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, + "cache_read_input_token_cost_above_32k_tokens": 2.34e-07, + "deprecation_date": "2026-10-09", + "input_cost_per_token": 6.5e-07, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "input_cost_per_token_above_32k_tokens": 1.17e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.25e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "output_cost_per_token_above_32k_tokens": 5.85e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 7.1e-08, + "cache_read_input_token_cost": 1.75e-08, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", + "output_cost_per_token": 3.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 1.1e-07, + "deprecation_date": "2026-10-09", + "input_cost_per_token": 2.3e-07, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", + "output_cost_per_token": 2.3e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/qwen/qwen3.6-plus": { + "cache_creation_input_token_cost": 4.0625e-07, + "input_cost_per_token_above_256k_tokens": 1.3e-06, + "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06, + "output_cost_per_token_above_256k_tokens": 3.9e-06, "input_cost_per_token": 3.25e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, @@ -31074,97 +43673,134 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.95e-06, - "source": "https://openrouter.ai/qwen/qwen3.6-plus", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 5e-08, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.95e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://openrouter.ai/qwen/qwen3.5-27b", + "output_cost_per_token": 1.56e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 2.6e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", + "output_cost_per_token": 2.08e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", + "output_cost_per_token": 2.6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 4e-07, - "input_cost_per_token_above_256k_tokens": 5e-07, + "input_cost_per_token": 2.6e-07, + "input_cost_per_token_above_256k_tokens": 3.25e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "output_cost_per_token_above_256k_tokens": 3e-06, - "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", + "output_cost_per_token": 1.56e-06, + "output_cost_per_token_above_256k_tokens": 1.95e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/qwen/qwen3.5-397b-a17b": { - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2.25e-07, + "input_cost_per_token": 5.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", + "output_cost_per_token": 3.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, "openrouter/switchpoint/router": { "input_cost_per_token": 8.5e-07, @@ -31178,14 +43814,23 @@ "supports_tool_choice": true }, "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 1.875e-06, + "input_cost_per_token": 3.5e-07, "litellm_provider": "openrouter", - "max_tokens": 4096, + "max_tokens": 5529, "mode": "chat", - "output_cost_per_token": 1.875e-06, - "supports_tool_choice": true, + "output_cost_per_token": 6.5e-07, + "supports_tool_choice": false, "max_input_tokens": 6144, - "max_output_tokens": 4096 + "max_output_tokens": 5529, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/x-ai/grok-4": { "input_cost_per_token": 3e-06, @@ -31202,18 +43847,24 @@ "supports_web_search": true }, "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4e-07, + "input_cost_per_token": 4.3e-07, "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, + "max_input_tokens": 204800, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.75e-06, - "source": "https://openrouter.ai/z-ai/glm-4.6", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8e-08, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/z-ai/glm-4.6:exacto": { "input_cost_per_token": 4.5e-07, @@ -31246,136 +43897,176 @@ "supports_prompt_caching": true }, "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, + "input_cost_per_token": 4.35e-07, + "output_cost_per_token": 8.7e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 3.6e-09, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 8e-08, + "cache_read_input_token_cost": 2.8e-09, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 1050000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": true, "supports_audio_input": true, + "supports_pdf_input": false, "supports_video_input": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, "openrouter/z-ai/glm-4.7": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.5e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.1e-07, + "deprecation_date": "2026-12-31", + "input_cost_per_token": 6e-07, "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_assistant_prefill": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 7e-08, + "input_cost_per_token": 6.05e-08, "output_cost_per_token": 4e-07, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-08, "litellm_provider": "openrouter", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false + "supports_vision": false, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_web_search": false }, "openrouter/z-ai/glm-5": { - "input_cost_per_token": 8e-07, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "openrouter", - "max_input_tokens": 202752, + "max_input_tokens": 204800, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.56e-06, - "source": "https://openrouter.ai/z-ai/glm-5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 1.05e-06, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 5.25e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.1", + "output_cost_per_token": 1.92e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 2.7e-07, + "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-08", "litellm_provider": "openrouter", - "max_input_tokens": 204000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_computer_use": false - }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_vision": false, "supports_prompt_caching": true, - "supports_computer_use": false + "supports_computer_use": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.5": { + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1.08e-06, + "cache_read_input_token_cost": 2.7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_computer_use": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_web_search": false }, "openrouter/openrouter/auto": { "input_cost_per_token": 0, @@ -31421,7 +44112,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -31435,7 +44126,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true @@ -31448,7 +44139,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": false, "supports_tool_choice": false @@ -31461,7 +44152,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true @@ -31474,7 +44165,7 @@ "max_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true @@ -31487,7 +44178,7 @@ "max_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true @@ -31500,7 +44191,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -31514,7 +44205,7 @@ "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false @@ -31527,7 +44218,7 @@ "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false @@ -31540,7 +44231,7 @@ "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, @@ -31554,7 +44245,7 @@ "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -31568,7 +44259,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, @@ -31582,7 +44273,7 @@ "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_reasoning": true, "supports_response_schema": true, @@ -31596,7 +44287,7 @@ "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false, @@ -31610,7 +44301,7 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, - "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", + "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_function_calling": false, "supports_response_schema": true, "supports_tool_choice": false @@ -31676,12 +44367,22 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "parallel_ai/search": { - "input_cost_per_query": 0.004, + "input_cost_per_query": 0.005, + "litellm_provider": "parallel_ai", + "mode": "search" + }, + "parallel_ai/search-fast": { + "input_cost_per_query": 0.001, "litellm_provider": "parallel_ai", "mode": "search" }, "parallel_ai/search-pro": { - "input_cost_per_query": 0.009, + "input_cost_per_query": 0.005, + "litellm_provider": "parallel_ai", + "mode": "search" + }, + "parallel_ai/search-turbo": { + "input_cost_per_query": 0.001, "litellm_provider": "parallel_ai", "mode": "search" }, @@ -31786,6 +44487,14 @@ "mode": "chat", "output_cost_per_token": 2.8e-07 }, + "perplexity/pplx-decider-v1-27b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/api-reference/decisions-post" + }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", @@ -32001,30 +44710,47 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "cache_read_input_token_cost": 1.75e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-7": { "supports_adaptive_thinking": true, @@ -32033,7 +44759,11 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", @@ -32041,21 +44771,33 @@ "supports_web_search": true, "supports_reasoning": false, "supports_function_calling": true, - "supports_output_config": true + "supports_output_config": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-3-pro-preview": { "litellm_provider": "perplexity", @@ -32069,7 +44811,11 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, - "supports_function_calling": true + "supports_function_calling": true, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/google/gemini-2.5-pro": { "litellm_provider": "perplexity", @@ -32098,6 +44844,62 @@ "mode": "responses", "supports_web_search": true, "supports_reasoning": false, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 6.25e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.3e-07, + "litellm_provider": "perplexity", + "mode": "responses", + "output_cost_per_token": 2.6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models", + "supports_web_search": true, + "supports_reasoning": true, + "supports_function_calling": true + }, + "perplexity/perplexity/glm-5.2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "perplexity", + "mode": "responses", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models", + "supports_web_search": true, + "supports_reasoning": true, + "supports_function_calling": true + }, + "perplexity/perplexity/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "perplexity", + "mode": "responses", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.perplexity.ai/docs/agent-api/models", + "supports_web_search": true, + "supports_reasoning": true, + "supports_function_calling": true + }, + "perplexity/perplexity/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "perplexity", + "mode": "responses", + "output_cost_per_token": 4e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models", + "supports_web_search": true, + "supports_reasoning": false, "supports_function_calling": true }, "perplexity/pplx-embed-v1-0.6b": { @@ -32159,7 +44961,7 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262000, "max_output_tokens": 65536, @@ -32169,7 +44971,8 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, @@ -32182,7 +44985,9 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "input_cost_per_token_batches": 1.1e-07, + "output_cost_per_token_batches": 4.4e-07 }, "qwen.qwen3-coder-30b-a3b-v1:0": { "input_cost_per_token": 1.5e-07, @@ -32213,40 +45018,146 @@ "qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 1.45e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, + "supports_native_structured_output": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.41e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.545e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.236e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.41e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.86e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.45e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": false }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "reducto/parse-legacy": { "litellm_provider": "reducto", @@ -32426,7 +45337,7 @@ "supports_tool_choice": true, "supports_response_schema": true }, - "replicateopenai/gpt-oss-20b": { + "replicate/openai/gpt-oss-20b": { "input_cost_per_token": 9e-08, "output_cost_per_token": 3.6e-07, "litellm_provider": "replicate", @@ -32445,7 +45356,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "prompt_cache_min_tokens": 4096 }, "replicate/ibm-granite/granite-3.3-8b-instruct": { "input_cost_per_token": 3e-08, @@ -32527,7 +45439,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "prompt_cache_min_tokens": 1024 }, "replicate/deepseek-ai/deepseek-v3": { "input_cost_per_token": 1.45e-06, @@ -32584,12 +45497,16 @@ "output_cost_per_token": 1.2e-05, "litellm_provider": "replicate", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_tool_choice": false, + "supports_response_schema": false, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "supports_audio_input": true, + "supports_video_input": true }, "replicate/anthropic/claude-4.5-sonnet": { "input_cost_per_token": 3e-06, @@ -32602,7 +45519,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "prompt_cache_min_tokens": 1024 }, "replicate/openai/gpt-4.1": { "input_cost_per_token": 2e-06, @@ -32657,17 +45575,19 @@ "supports_response_schema": true }, "replicate/google/gemini-2.5-flash": { - "input_cost_per_token": 2.5e-06, + "input_cost_per_token": 3e-07, "output_cost_per_token": 2.5e-06, "litellm_provider": "replicate", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_image_size": false + "supports_tool_choice": false, + "supports_response_schema": false, + "supports_image_size": false, + "supports_reasoning": true, + "supports_video_input": true }, "replicate/openai/gpt-oss-120b": { "input_cost_per_token": 1.8e-07, @@ -32709,16 +45629,6 @@ "supports_reasoning": true, "supports_system_messages": true }, - "rerank-english-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -32729,16 +45639,6 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, - "rerank-multilingual-v2.0": { - "input_cost_per_query": 0.002, - "input_cost_per_token": 0.0, - "litellm_provider": "cohere", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "rerank", - "output_cost_per_token": 0.0 - }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, @@ -32759,6 +45659,28 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, + "rerank-v4.0-fast": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/pricing" + }, + "rerank-v4.0-pro": { + "input_cost_per_query": 0.0025, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cohere.com/pricing" + }, "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { "input_cost_per_query": 0.0, "input_cost_per_token": 0.0, @@ -32857,31 +45779,6 @@ "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2026-03-20", - "input_cost_per_token": 7e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 3e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/Llama-4-Maverick-17B-128E-Instruct": { "input_cost_per_token": 6.3e-07, "litellm_provider": "sambanova", @@ -32899,73 +45796,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-06, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 1e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 4e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-08, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 8e-08, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.6e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, "sambanova/Meta-Llama-3.3-70B-Instruct": { "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", @@ -32979,54 +45809,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "sambanova/Meta-Llama-Guard-3-8B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 3e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/QwQ-32B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 5e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_audio_input": true - }, - "sambanova/Qwen3-32B": { - "deprecation_date": "2026-04-06", - "input_cost_per_token": 4e-07, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/DeepSeek-V3.1": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -33076,6 +45858,40 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "scx-ai/GLM-5.2": { + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 6.1e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.98e-06, + "source": "https://scx.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "scx-ai/Qwen3.8-Max": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.99e-06, + "source": "https://scx.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "snowflake/claude-3-5-sonnet": { "litellm_provider": "snowflake", "max_input_tokens": 200000, @@ -33585,24 +46401,6 @@ "mode": "image_generation", "output_cost_per_image": 0.14 }, - "standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, - "standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "litellm_provider": "openai", - "mode": "image_generation", - "output_cost_per_pixel": 0.0 - }, "linkup/search": { "input_cost_per_query": 0.00587, "litellm_provider": "linkup", @@ -33649,7 +46447,7 @@ "source": "https://docs.mistral.ai/capabilities/code_generation/" }, "text-embedding-004": { - "deprecation_date": "2026-01-14", + "deprecation_date": "2027-04-01", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -33661,6 +46459,7 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" }, "text-embedding-005": { + "deprecation_date": "2027-04-01", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -33680,7 +46479,8 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, - "output_vector_size": 3072 + "output_vector_size": 3072, + "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-3-small": { "input_cost_per_token": 2e-08, @@ -33691,7 +46491,8 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, - "output_vector_size": 1536 + "output_vector_size": 1536, + "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-ada-002": { "input_cost_per_token": 1e-07, @@ -33700,7 +46501,8 @@ "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "output_vector_size": 1536 + "output_vector_size": 1536, + "source": "https://developers.openai.com/api/docs/pricing" }, "text-embedding-ada-002-v2": { "input_cost_per_token": 1e-07, @@ -33733,34 +46535,8 @@ "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "text-moderation-007": { - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-latest": { - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, - "text-moderation-stable": { - "input_cost_per_token": 0.0, - "litellm_provider": "openai", - "max_input_tokens": 32768, - "max_output_tokens": 0, - "max_tokens": 0, - "mode": "moderation", - "output_cost_per_token": 0.0 - }, "text-multilingual-embedding-002": { + "deprecation_date": "2027-04-01", "input_cost_per_character": 2.5e-08, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", @@ -33856,93 +46632,17 @@ "mode": "chat", "output_cost_per_token": 1e-07 }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "input_cost_per_token": 6.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_tool_choice": false - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "input_cost_per_token": 2e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "input_cost_per_token": 3e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "mode": "chat", - "output_cost_per_token": 7e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "input_cost_per_token": 5.5e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.19e-06, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 3e-07, + "max_input_tokens": 32768, + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 1.25e-06, @@ -33950,6 +46650,9 @@ "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, + "metadata": { + "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" + }, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_function_calling": true, @@ -33957,118 +46660,14 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.7e-06, - "source": "https://www.together.ai/models/deepseek-v3-1", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 16384 - }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, + "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8.8e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "input_cost_per_token": 0, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 2.7e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.5e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 5.9e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "input_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "input_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 1.04e-06, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -34077,6 +46676,9 @@ "together_ai/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", + "metadata": { + "successor": "together_ai/moonshotai/Kimi-K3" + }, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://www.together.ai/models/kimi-k2-instruct", @@ -34089,29 +46691,16 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://www.together.ai/models/gpt-oss-120b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/openai/gpt-oss-20b": { - "input_cost_per_token": 5e-08, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://www.together.ai/models/gpt-oss-20b", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { "litellm_provider": "together_ai", "mode": "chat", @@ -34119,123 +46708,289 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "input_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.1e-06, - "source": "https://www.together.ai/models/glm-4-5-air", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_input_tokens": 202752, + "max_tokens": 202752, + "metadata": { + "successor": "together_ai/zai-org/GLM-5.2" + }, "mode": "chat", "output_cost_per_token": 2.2e-06, - "source": "https://www.together.ai/models/glm-4-6", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.7": { - "input_cost_per_token": 4.5e-07, + "together_ai/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_input_tokens": 524288, + "max_tokens": 524288, "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/glm-4-7", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/Prism-ML/Ternary-Bonsai-27B": { + "input_cost_per_token": 0.0, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.together.ai/docs/serverless-models" + }, + "together_ai/Qwen/Qwen3.5-9B": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "together_ai/moonshotai/Kimi-K2.5": { + "together_ai/Qwen/Qwen3.6-Plus": { "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.8e-06, - "source": "https://www.together.ai/models/kimi-k2-5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_reasoning": true - }, - "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "input_cost_per_token": 1e-06, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://www.together.ai/models/kimi-k2-0905", + "source": "https://api.together.ai/v1/models", + "supports_reasoning": true + }, + "together_ai/Qwen/Qwen3.7-Max": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true + }, + "together_ai/Qwen/Qwen3.7-Plus": { + "input_cost_per_token": 3.2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.28e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3.8-2.4T-A95B": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1010000, + "max_tokens": 1010000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true + }, + "together_ai/arize-ai/qwen-2-1.5b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-09-29", + "input_cost_per_token": 1.4e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "input_cost_per_token": 1.5e-07, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.3e-07, + "deprecation_date": "2026-09-29", + "input_cost_per_token": 1.32e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-models/Muse-Glimmer-30B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", + "source": "https://api.together.ai/v1/models", + "supports_prompt_caching": true + }, + "together_ai/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/thinkingmachines/Inkling": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 4.05e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "together_ai/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048575, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048575, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", - "max_input_tokens": 262144, + "max_input_tokens": 1048575, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", + "output_cost_per_token": 5e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "input_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 3.6e-06, - "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "tts-1": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, "tts-1-hd": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ] }, + "transcribe/StartTranscriptionJob": { + "input_cost_per_second": 0.0001, + "litellm_provider": "transcribe", + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://aws.amazon.com/transcribe/pricing/", + "metadata": { + "notes": "Amazon Transcribe standard batch transcription, billed per second of audio with no minimum. Same rate in every region of the AWS Price List offer file for transcribe (checked 2026-09-17)" + } + }, "aws_polly/standard": { "input_cost_per_character": 4e-06, "litellm_provider": "aws_polly", @@ -34273,6 +47028,7 @@ "source": "https://aws.amazon.com/polly/pricing/" }, "us.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -34284,9 +47040,11 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "us.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -34296,23 +47054,11 @@ "output_cost_per_token": 1.4e-07, "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-premier-v1:0": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "max_tokens": 10000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true }, "us.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -34324,7 +47070,8 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -34350,12 +47097,13 @@ "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -34367,7 +47115,9 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-07, + "output_cost_per_token_batches": 2.75e-06 }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -34424,22 +47174,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 3.125e-07 - }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", @@ -34455,25 +47189,10 @@ "cache_read_input_token_cost": 1.5e-06, "cache_creation_input_token_cost": 1.875e-05 }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06 - }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2027-01-08", "input_cost_per_token": 1.5e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, @@ -34495,7 +47214,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -34508,6 +47228,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -34529,7 +47250,10 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 1.65e-06, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -34542,6 +47266,7 @@ "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.44e-05, "cache_read_input_token_cost_above_200k_tokens": 7.2e-07, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -34558,7 +47283,295 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "us-gov.anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us-gov.anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us-gov.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us-gov.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "us-gov.anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_1hr": 2.4e-05, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.2e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "us-gov.nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "us-gov.nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true + }, + "us-gov.nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": false + }, + "us-gov.nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "us-gov.openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 8.4e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "us-gov.openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "us-gov.xai.grok-4.6": { + "supports_regex_lookaround": false, + "input_cost_per_token": 2.64e-06, + "output_cost_per_token": 7.92e-06, + "cache_read_input_token_cost": 6.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -34566,6 +47579,7 @@ "cache_read_input_token_cost": 1.1e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -34582,7 +47596,10 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-07, + "output_cost_per_token_batches": 2.75e-06, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -34616,6 +47633,7 @@ "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -34639,7 +47657,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -34647,6 +47666,7 @@ "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -34670,18 +47690,21 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 5.5e-06, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -34700,11 +47723,13 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-10-14", "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, @@ -34731,7 +47756,8 @@ "supports_tool_choice": true, "supports_vision": true, "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.deepseek.r1-v1:0": { "input_cost_per_token": 1.35e-06, @@ -34741,6 +47767,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.4e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false @@ -34755,7 +47782,11 @@ "output_cost_per_token": 1.85e-06, "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "eu.deepseek.v3.2": { "input_cost_per_token": 7.4e-07, @@ -34767,27 +47798,33 @@ "output_cost_per_token": 2.22e-06, "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_native_structured_output": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 9.9e-07, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, @@ -34803,13 +47840,14 @@ "supports_tool_choice": false }, "us.meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "input_cost_per_token": 1.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -34837,13 +47875,14 @@ "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true @@ -34909,6 +47948,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_tool_choice": false }, @@ -35222,7 +48262,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-opus-4": { "cache_creation_input_token_cost": 1.875e-05, @@ -35241,7 +48282,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-opus-4.1": { "cache_creation_input_token_cost": 1.875e-05, @@ -35260,7 +48302,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-opus-4.5": { "cache_creation_input_token_cost": 6.25e-06, @@ -35280,10 +48323,12 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true + "supports_output_config": true, + "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-opus-4.6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -35301,7 +48346,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true + "supports_output_config": true, + "prompt_cache_min_tokens": 4096 }, "vercel_ai_gateway/anthropic/claude-sonnet-4": { "cache_creation_input_token_cost": 3.75e-06, @@ -35320,7 +48366,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/anthropic/claude-sonnet-4.5": { "cache_creation_input_token_cost": 3.75e-06, @@ -35338,7 +48385,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024 }, "vercel_ai_gateway/cohere/command-a": { "input_cost_per_token": 2.5e-06, @@ -35415,34 +48463,6 @@ "output_cost_per_token": 9e-07, "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 1.5e-07, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 7.5e-08, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-07, "litellm_provider": "vercel_ai_gateway", @@ -35455,10 +48475,15 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_image_size": false + "supports_image_size": false, + "cache_read_input_token_cost": 3e-08, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_web_search": true, + "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemini-2.5-pro": { - "input_cost_per_token": 2.5e-06, + "input_cost_per_token": 1.25e-06, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -35468,7 +48493,15 @@ "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_response_schema": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_web_search": true, + "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemini-embedding-001": { "input_cost_per_token": 1.5e-07, @@ -36204,10 +49237,26 @@ "mode": "audio_transcription", "source": "https://cloud.google.com/speech-to-text/pricing", "supported_endpoints": [ - "/v1/audio/transcriptions" + "/v1/audio/transcriptions", + "/v1/realtime" + ] + }, + "vertex_ai/chirp_2": { + "input_cost_per_second": 0.00026667, + "litellm_provider": "vertex_ai", + "metadata": { + "calculation": "$0.016/60 seconds = $0.00026667 per second", + "original_pricing_per_minute": 0.016 + }, + "mode": "audio_transcription", + "source": "https://cloud.google.com/speech-to-text/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime" ] }, "vertex_ai/claude-3-5-haiku": { + "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36221,6 +49270,7 @@ "supports_tool_choice": true }, "vertex_ai/claude-3-5-haiku@20241022": { + "deprecation_date": "2026-07-05", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36234,17 +49284,23 @@ "supports_tool_choice": true }, "vertex_ai/claude-haiku-4-5": { + "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "output_cost_per_token_batches": 2.5e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -36257,17 +49313,23 @@ "prompt_cache_min_tokens": 4096 }, "vertex_ai/claude-haiku-4-5@20251001": { + "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "output_cost_per_token_batches": 2.5e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -36280,6 +49342,7 @@ "prompt_cache_min_tokens": 4096 }, "vertex_ai/claude-3-5-sonnet": { + "deprecation_date": "2026-02-19", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36295,6 +49358,7 @@ "supports_vision": true }, "vertex_ai/claude-3-5-sonnet@20240620": { + "deprecation_date": "2026-02-19", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36308,29 +49372,8 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-11", - "input_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-haiku": { + "deprecation_date": "2026-08-23", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36344,6 +49387,7 @@ "supports_vision": true }, "vertex_ai/claude-3-haiku@20240307": { + "deprecation_date": "2026-08-23", "input_cost_per_token": 2.5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36357,6 +49401,7 @@ "supports_vision": true }, "vertex_ai/claude-3-opus": { + "deprecation_date": "2025-08-01", "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36370,6 +49415,7 @@ "supports_vision": true }, "vertex_ai/claude-3-opus@20240229": { + "deprecation_date": "2025-08-01", "input_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36408,80 +49454,23 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-opus-4": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-opus-4-1": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 7.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "output_cost_per_token_batches": 3.75e-05, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-opus-4-5": { + "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36497,19 +49486,26 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-5@20251101": { + "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36526,20 +49522,28 @@ "supports_vision": true, "supports_native_streaming": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6": { + "deprecation_date": "2027-02-05", + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36556,20 +49560,28 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6@default": { + "deprecation_date": "2027-02-05", + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36586,20 +49598,27 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7": { + "deprecation_date": "2027-04-16", + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36617,20 +49636,27 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7@default": { + "deprecation_date": "2027-04-16", + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36648,12 +49674,57 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5": { + "deprecation_date": "2027-06-08", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-fable-5-1": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -36667,9 +49738,12 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -36678,12 +49752,61 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5@default": { + "deprecation_date": "2027-06-08", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-fable-5-1@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -36697,6 +49820,51 @@ "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-opus-5": { + "deprecation_date": "2027-01-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -36708,20 +49876,150 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_max_reasoning_effort": true + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-opus-5@default": { + "deprecation_date": "2027-01-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-opus-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-opus-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8": { + "deprecation_date": "2027-05-28", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36739,20 +50037,28 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8@default": { + "deprecation_date": "2027-05-28", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36770,17 +50076,21 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5": { + "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36789,6 +50099,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, + "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -36798,19 +50109,26 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { + "deprecation_date": "2026-12-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -36829,20 +50147,27 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6": { + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -36859,17 +50184,21 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5@20250929": { + "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -36878,6 +50207,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, + "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -36888,96 +50218,9 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-opus-4@20250514": { - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-sonnet-4@20250514": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -36987,6 +50230,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -36998,6 +50242,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37009,6 +50254,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37020,6 +50266,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37057,14 +50304,18 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 1.35e-06, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2026-10-21", + "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5.4e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token": 1.7e-06, + "output_cost_per_token_batches": 8.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -37075,6 +50326,8 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { + "cache_read_input_token_cost": 5.6e-08, + "deprecation_date": "2026-10-21", "input_cost_per_token": 5.6e-07, "input_cost_per_token_batches": 2.8e-07, "litellm_provider": "vertex_ai-deepseek_models", @@ -37084,7 +50337,7 @@ "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -37095,14 +50348,17 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "deprecation_date": "2026-10-21", "input_cost_per_token": 1.35e-06, + "input_cost_per_token_batches": 6.75e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 2.7e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -37113,9 +50369,11 @@ "supports_tool_choice": true }, "vertex_ai/gemini-2.5-flash-image": { - "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2027-03-15", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -37125,8 +50383,10 @@ "output_cost_per_image_token": 3e-05, "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, "rpm": 100000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -37158,9 +50418,20 @@ "supports_image_size": false }, "vertex_ai/gemini-3-pro-image": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -37169,13 +50440,25 @@ "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, @@ -37185,13 +50468,22 @@ "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, "vertex_ai/gemini-3.1-flash-image": { + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -37200,12 +50492,17 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_batches": 2.5e-08, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -37214,9 +50511,53 @@ "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, + "vertex_ai/gemini-3.1-flash-lite-image": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "deprecation_date": "2027-06-28", + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true + }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 5e-07, @@ -37263,10 +50604,14 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-08, + "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_audio_token": 5e-07, @@ -37274,6 +50619,7 @@ "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, "input_cost_per_token_priority": 4.5e-07, + "input_cost_per_audio_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -37284,7 +50630,8 @@ "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, "output_cost_per_token_priority": 2.7e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -37319,9 +50666,72 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-07 + }, + "vertex_ai/gemini-3.5-flash-lite": { + "deprecation_date": "2027-07-21", + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_batches": 1.5e-08, + "cache_read_input_token_cost_flex": 1.5e-08, + "cache_read_input_token_cost_priority": 5.4e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "regional_endpoint_uplift_multiplier": 1.1, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/deep-research-pro-preview-12-2025": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -37334,58 +50744,10 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" - }, - "vertex_ai/imagegeneration@006": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-fast-generate-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-002": { - "deprecation_date": "2025-11-10", - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-capability-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects" - }, - "vertex_ai/imagen-4.0-fast-generate-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.02, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-generate-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.04, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-ultra-generate-001": { - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "output_cost_per_image": 0.06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/jamba-1.5": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -37396,6 +50758,7 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -37406,6 +50769,7 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-large@001": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-06, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -37416,6 +50780,7 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -37426,6 +50791,7 @@ "supports_tool_choice": true }, "vertex_ai/jamba-1.5-mini@001": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, @@ -37435,6 +50801,99 @@ "output_cost_per_token": 4e-07, "supports_tool_choice": true }, + "vertex_ai/lyria-002": { + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", + "supported_audio_formats": [ + "wav" + ], + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true, + "vertex_ai_audio_api": "lyria_predict" + }, + "vertex_ai/lyria-3-clip-preview": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "audio_speech", + "output_cost_per_image": 0.04, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", + "supported_audio_formats": [ + "mp3" + ], + "supported_endpoints": [ + "/v1beta/interactions", + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supported_regions": [ + "global" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "vertex_ai_audio_api": "lyria_interactions" + }, + "vertex_ai/lyria-3-pro-preview": { + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "audio_speech", + "output_cost_per_image": 0.08, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria", + "supported_audio_formats": [ + "mp3", + "wav" + ], + "supported_endpoints": [ + "/v1beta/interactions", + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supported_regions": [ + "global" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "vertex_ai_audio_api": "lyria_interactions" + }, "vertex_ai/meta/llama-3.1-405b-instruct-maas": { "input_cost_per_token": 5e-06, "litellm_provider": "vertex_ai-llama_models", @@ -37495,13 +50954,15 @@ }, "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { "input_cost_per_token": 3.5e-07, + "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 5.75e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -37555,13 +51016,15 @@ }, "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 3.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -37607,6 +51070,8 @@ "supports_tool_choice": true }, "vertex_ai/minimaxai/minimax-m2-maas": { + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-21", "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, @@ -37614,11 +51079,13 @@ "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/moonshotai/kimi-k2-thinking-maas": { + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2026-10-21", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, @@ -37626,12 +51093,14 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2026-10-21", "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, @@ -37639,7 +51108,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -37649,6 +51118,7 @@ }, "vertex_ai/zai-org/glm-5-maas": { "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2026-10-21", "input_cost_per_token": 1e-06, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, @@ -37656,7 +51126,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -37673,6 +51143,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37684,6 +51155,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37695,6 +51167,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37706,6 +51179,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -37776,27 +51250,29 @@ "supports_tool_choice": true }, "vertex_ai/mistral-small-2503": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-small-2503@001": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 3e-07, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-ocr-2505": { "litellm_provider": "vertex_ai", @@ -37808,20 +51284,22 @@ "source": "https://cloud.google.com/generative-ai-app-builder/pricing" }, "vertex_ai/deepseek-ai/deepseek-ocr-maas": { + "deprecation_date": "2026-10-21", "litellm_provider": "vertex_ai", "mode": "ocr", "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "ocr_cost_per_page": 0.0003, - "source": "https://cloud.google.com/vertex-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ] }, "vertex_ai/google/gemma-4-26b-a4b-it-maas": { + "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-openai_models", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -37835,38 +51313,45 @@ "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 4.5e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "output_cost_per_token": 3.6e-07, + "output_cost_per_token_batches": 1.8e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { - "input_cost_per_token": 7.5e-08, + "deprecation_date": "2026-10-21", + "input_cost_per_token": 7e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", - "supports_reasoning": true + "output_cost_per_token": 2.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_reasoning": true, + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token_batches": 3.5e-08, + "output_cost_per_token_batches": 1.25e-07 }, "vertex_ai/xai/grok-4.1-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -37876,13 +51361,14 @@ "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 2e-07, "litellm_provider": "vertex_ai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -37891,15 +51377,19 @@ }, "vertex_ai/xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -37907,30 +51397,77 @@ }, "vertex_ai/xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, + "vertex_ai/xai/grok-4.3": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/xai/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-07, + "deprecation_date": "2026-10-21", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token": 8.8e-07, + "output_cost_per_token_batches": 4.4e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global", "us-south1" @@ -37939,14 +51476,18 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 2.2e-08, + "deprecation_date": "2026-10-21", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_batches": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -37954,6 +51495,7 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { + "deprecation_date": "2026-10-21", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -37961,7 +51503,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -37969,6 +51511,7 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { + "deprecation_date": "2026-10-21", "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, @@ -37976,62 +51519,21 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], "supports_function_calling": true, "supports_tool_choice": true }, - "vertex_ai/veo-2.0-generate-001": { - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.35, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-fast-generate-001": { - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, - "vertex_ai/veo-3.0-generate-001": { - "litellm_provider": "vertex_ai-video-models", - "max_input_tokens": 1024, - "max_tokens": 1024, - "mode": "video_generation", - "output_cost_per_second": 0.4, - "source": "https://ai.google.dev/gemini-api/docs/video", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ] - }, "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "output_cost_per_second_4k": 0.6, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -38044,8 +51546,10 @@ "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_4k": 0.3, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -38054,12 +51558,14 @@ ] }, "vertex_ai/veo-3.1-generate-001": { + "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "output_cost_per_second_4k": 0.6, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -38068,12 +51574,15 @@ ] }, "vertex_ai/veo-3.1-fast-generate-001": { + "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, "max_tokens": 1024, "mode": "video_generation", - "output_cost_per_second": 0.15, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "output_cost_per_second_4k": 0.3, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -38081,6 +51590,22 @@ "video" ] }, + "vertex_ai/veo-3.1-lite-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_1080p": 0.08, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, "voyage/rerank-2": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", @@ -38099,6 +51624,26 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, + "voyage/rerank-1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/rerank-lite-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/rerank-2.5": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", @@ -38117,6 +51662,26 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, + "voyage/rerank-3": { + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/rerank-3-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-2": { "input_cost_per_token": 1e-07, "litellm_provider": "voyage", @@ -38133,6 +51698,16 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, + "voyage/voyage-multilingual-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-3-large": { "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", @@ -38205,6 +51780,16 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, + "voyage/voyage-large-2-instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-law-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", @@ -38238,67 +51823,26 @@ "output_cost_per_token": 0.0 }, "wandb/openai/gpt-oss-120b": { + "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, - "input_cost_per_token": 0.015, - "output_cost_per_token": 0.06, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-20b": { + "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, - "input_cost_per_token": 0.005, - "output_cost_per_token": 0.02, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/zai-org/GLM-4.5": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.2, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.1, - "output_cost_per_token": 0.15, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.01, - "output_cost_per_token": 0.01, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { "max_tokens": 262144, @@ -38315,81 +51859,36 @@ "supports_response_schema": true, "supports_vision": true }, - "wandb/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 197000, - "max_input_tokens": 197000, - "max_output_tokens": 197000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true - }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "max_output_tokens": 128000, - "input_cost_per_token": 0.022, - "output_cost_per_token": 0.022, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V3.1": { + "supports_reasoning": true, "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 161000, "max_output_tokens": 128000, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.165, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 1.65e-06, "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.135, - "output_cost_per_token": 0.54, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.114, - "output_cost_per_token": 0.275, - "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.071, - "output_cost_per_token": 0.071, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 7.1e-07, "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 64000, - "max_input_tokens": 64000, - "max_output_tokens": 64000, - "input_cost_per_token": 0.017, - "output_cost_per_token": 0.066, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/microsoft/Phi-4-mini-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.008, - "output_cost_per_token": 0.035, - "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "watsonx/ibm/granite-3-8b-instruct": { "input_cost_per_token": 2e-07, @@ -38428,16 +51927,30 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0005, - "output_cost_per_token": 0.002, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/bigscience/mt0-xxl": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.908e-06, + "output_cost_per_token": 1.908e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { "max_tokens": 8192, @@ -38500,16 +52013,17 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 20480, - "max_input_tokens": 20480, - "max_output_tokens": 20480, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.5e-07, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6.36e-08, + "output_cost_per_token": 2.65e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { "max_tokens": 8192, @@ -38632,28 +52146,43 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 7.1e-07, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 7.526e-07, + "output_cost_per_token": 7.526e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.4e-06, + "max_tokens": 8192, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" + }, + "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { + "max_tokens": 8192, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "input_cost_per_token": 3.71e-07, + "output_cost_per_token": 1.484e-06, + "litellm_provider": "watsonx", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { "max_tokens": 128000, @@ -38692,16 +52221,17 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "max_tokens": 16384, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "input_cost_per_token": 1.06e-07, + "output_cost_per_token": 3.18e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { "max_tokens": 128000, @@ -38716,16 +52246,17 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.59e-07, + "output_cost_per_token": 6.36e-07, "litellm_provider": "watsonx", "mode": "chat", "supports_function_calling": false, "supports_parallel_function_calling": false, - "supports_vision": false + "supports_vision": false, + "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { "max_tokens": 8192, @@ -38755,533 +52286,116 @@ "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" - ] - }, - "xai/grok-2": { - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-1212": { - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-latest": { - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision": { - "input_cost_per_image": 2e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "xai/grok-2-vision-1212": { - "deprecation_date": "2026-02-28", - "input_cost_per_image": 2e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "xai/grok-2-vision-latest": { - "input_cost_per_image": 2e-06, - "input_cost_per_token": 2e-06, - "litellm_provider": "xai", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "xai/grok-3": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-3-beta": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-fast-beta": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 5e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-fast-latest": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 5e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-latest": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini": { - "cache_read_input_token_cost": 7.5e-08, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 3e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini-beta": { - "cache_read_input_token_cost": 7.5e-08, - "deprecation_date": "2026-02-28", - "input_cost_per_token": 3e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini-fast": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini-fast-beta": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini-fast-latest": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3-mini-latest": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-4": { - "input_cost_per_token": 3e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-4-fast-reasoning": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-fast-non-reasoning": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-0709": { - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_128k_tokens": 6e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_128k_tokens": 3e-05, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-latest": { - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_128k_tokens": 6e-06, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_128k_tokens": 3e-05, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-4-1-fast": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "xai/grok-4-1-fast-reasoning": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-1-fast-reasoning-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-1-fast-non-reasoning": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-4-1-fast-non-reasoning-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_128k_tokens": 4e-07, - "litellm_provider": "xai", - "max_input_tokens": 2000000.0, - "max_output_tokens": 2000000.0, - "max_tokens": 2000000.0, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_128k_tokens": 1e-06, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15" + ], + "deprecation_date": "2027-02-26", + "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-4.20-multi-agent-beta-0309": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] }, "xai/grok-4.20-beta-0309-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, "xai/grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true }, "xai/grok-4.20-beta-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, + "input_cost_per_token": 1.25e-06, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true }, "xai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -39289,7 +52403,9 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -39301,8 +52417,13 @@ "xai/grok-4.3-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -39310,7 +52431,9 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -39320,8 +52443,9 @@ "supports_web_search": true }, "xai/grok-4.5": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", @@ -39331,7 +52455,7 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -39341,8 +52465,9 @@ "supports_web_search": true }, "xai/grok-4.5-latest": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_image_token": 2e-06, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", @@ -39352,7 +52477,7 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -39361,76 +52486,68 @@ "supports_vision": true, "supports_web_search": true }, - "xai/grok-beta": { - "input_cost_per_token": 5e-06, + "xai/grok-build-latest": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_image_token": 2e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true }, - "xai/grok-code-fast": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, + "xai/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_image_token": 2e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "xai/grok-code-fast-1": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "deprecation_date": "2026-05-15" + "supports_vision": true, + "supports_web_search": true }, - "xai/grok-code-fast-1-0825": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, + "xai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_image_token": 2e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "deprecation_date": "2026-05-15" - }, - "xai/grok-vision-beta": { - "input_cost_per_image": 5e-06, - "input_cost_per_token": 5e-06, - "litellm_provider": "xai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true @@ -39438,16 +52555,19 @@ "zai.glm-4.7": { "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 203000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, @@ -39459,23 +52579,30 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, + "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai.glm-4.7-flash": { "input_cost_per_token": 7e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 203000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai/glm-5": { "cache_creation_input_token_cost": 0, @@ -39492,6 +52619,37 @@ "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing" }, + "zai/glm-5.3": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "zai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.z.ai/guides/overview/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "zai/glm-5.3-flash": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "zai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing", + "supports_vision": true + }, "zai/glm-5.1": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 2.6e-07, @@ -39656,6 +52814,7 @@ "mode": "chat" }, "openai/sora-2": { + "deprecation_date": "2026-09-24", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -39669,6 +52828,7 @@ ] }, "openai/sora-2-pro": { + "deprecation_date": "2026-09-24", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, @@ -39683,6 +52843,7 @@ }, "openai/sora-2-pro-high-res": { "litellm_provider": "openai", + "deprecation_date": "2026-09-24", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, "source": "https://platform.openai.com/docs/api-reference/videos", @@ -39695,10 +52856,11 @@ ] }, "azure/sora-2": { + "deprecation_date": "2026-10-15", "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, - "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "source": "https://ai.azure.com/catalog/models/sora-2", "supported_modalities": [ "text" ], @@ -39710,7 +52872,7 @@ "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, - "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "source": "https://ai.azure.com/catalog/models/sora-2-pro", "supported_modalities": [ "text" ], @@ -39722,7 +52884,7 @@ "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, - "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "source": "https://ai.azure.com/catalog/models/sora-2-pro", "supported_modalities": [ "text" ], @@ -39746,10 +52908,10 @@ "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" } }, - "runwayml/gen4_aleph": { + "runwayml/gen4.5": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_video_per_second": 0.15, + "output_cost_per_second": 0.12, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -39759,13 +52921,136 @@ "video" ], "metadata": { - "comment": "15 credits per second @ $0.01 per credit = $0.15 per second" + "comment": "12 credits per second @ $0.01 per credit = $0.12 per second" } }, - "runwayml/gen3a_turbo": { + "runwayml/aleph2": { "litellm_provider": "runwayml", "mode": "video_generation", - "output_cost_per_video_per_second": 0.05, + "output_cost_per_second": 0.28, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "28 credits per second @ $0.01 per credit = $0.28 per second; 56 credit minimum per task not modeled" + } + }, + "runwayml/seedance2": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.36, + "output_cost_per_second_1080p": 0.4, + "output_cost_per_second_4k": 1.5, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "36 credits per second at 480p/720p, 40 at 1080p, 150 at 4K @ $0.01 per credit" + } + }, + "runwayml/seedance2_fast": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.29, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "29 credits per second at 480p/720p @ $0.01 per credit = $0.29 per second" + } + }, + "runwayml/seedance2_mini": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.16, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "16 credits per second @ $0.01 per credit = $0.16 per second; 64 credit minimum per task not modeled" + } + }, + "runwayml/seedance2_5": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.3, + "output_cost_per_second_480p": 0.2, + "output_cost_per_second_1080p": 0.68, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "Output: 20/30/68 credits per second at 480p/720p/1080p @ $0.01 per credit; input video billed additionally at 10/15/34 credits per input second and the 80 credit minimum per task are not modeled" + } + }, + "runwayml/hailuo3": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.15, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "10 credits per second at 768P, 15 at 2K (mapped to the 1080p tier) @ $0.01 per credit; 2 credits per reference image not modeled" + } + }, + "runwayml/gemini_omni_flash": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.1, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "10 credits per second @ $0.01 per credit = $0.10 per second" + } + }, + "runwayml/veo3.1": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.4, "source": "https://docs.dev.runwayml.com/guides/pricing/", "supported_modalities": [ "text", @@ -39775,7 +53060,23 @@ "video" ], "metadata": { - "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" + "comment": "40 credits per second with audio, 20 without @ $0.01 per credit; priced at the with-audio rate" + } + }, + "runwayml/veo3.1_fast": { + "litellm_provider": "runwayml", + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "metadata": { + "comment": "15 credits per second with audio, 10 without @ $0.01 per credit; priced at the with-audio rate" } }, "runwayml/gen4_image": { @@ -41647,10 +54948,11 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 0.0, + "input_cost_per_token": 2e-07, "output_cost_per_token": 0.0, "litellm_provider": "fireworks_ai", - "mode": "rerank" + "mode": "rerank", + "source": "https://api.fireworks.ai/v1/serverless/models" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { "max_tokens": 262144, @@ -41715,7 +55017,7 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -41884,11 +55186,12 @@ }, "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 2e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -41900,11 +55203,12 @@ }, "fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast": { "cache_read_input_token_cost": 3.8e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 1.9e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -41962,7 +55266,8 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, - "supports_function_calling": true + "supports_function_calling": true, + "deprecation_date": "2026-10-01" }, "scaleway/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, @@ -41992,28 +55297,6 @@ "supports_reasoning": true, "supports_vision": true }, - "scaleway/google/gemma-3-27b-it": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 40000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5e-07, - "supports_function_calling": true, - "supports_vision": true - }, - "scaleway/hcompany/holo2-30b-a3b": { - "input_cost_per_token": 3e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 22000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "supports_reasoning": true, - "supports_vision": true - }, "scaleway/mistralai/mistral-medium-3.5-128b": { "input_cost_per_token": 1.5e-06, "litellm_provider": "scaleway", @@ -42027,27 +55310,6 @@ "supports_vision": true, "supports_tool_choice": true }, - "scaleway/mistralai/devstral-2-123b-instruct-2512": { - "input_cost_per_token": 4e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-06, - "supports_function_calling": true - }, - "scaleway/mistralai/voxtral-small-24b-2507": { - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "scaleway", - "max_input_tokens": 32000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3.5e-07, - "supports_audio_input": true - }, "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": { "input_cost_per_token": 1.5e-07, "litellm_provider": "scaleway", @@ -42068,7 +55330,8 @@ "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, - "supports_function_calling": true + "supports_function_calling": true, + "deprecation_date": "2026-10-01" }, "scaleway/BAAI/bge-multilingual-gemma2": { "input_cost_per_token": 1e-07, @@ -42139,8 +55402,8 @@ "novita/xiaomimimo/mimo-v2-flash": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, "max_tokens": 32000, @@ -42149,8 +55412,8 @@ "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token_cache_hit": 2e-08, + "cache_read_input_token_cost": 2.4e-08, + "input_cost_per_token_cache_hit": 2.4e-08, "supports_reasoning": true }, "novita/zai-org/autoglm-phone-9b-multilingual": { @@ -42170,14 +55433,16 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true }, "novita/minimax/minimax-m2": { "litellm_provider": "novita", @@ -42193,7 +55458,8 @@ "supports_system_messages": true, "cache_read_input_token_cost": 3e-08, "input_cost_per_token_cache_hit": 3e-08, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/paddlepaddle/paddleocr-vl": { "litellm_provider": "novita", @@ -42231,7 +55497,9 @@ "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/zai-org/glm-4.6v": { "litellm_provider": "novita", @@ -42296,7 +55564,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_reasoning": true }, "novita/qwen/qwen3-next-80b-a3b-thinking": { "litellm_provider": "novita", @@ -42408,8 +55677,8 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -42419,8 +55688,8 @@ "novita/qwen/qwen3-coder-480b-a35b-instruct": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.3e-06, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, @@ -42455,7 +55724,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true @@ -42466,8 +55735,8 @@ "input_cost_per_token": 5.7e-07, "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -42480,8 +55749,8 @@ "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -42528,7 +55797,8 @@ "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/google/gemma-3-12b-it": { "litellm_provider": "novita", @@ -42570,7 +55840,7 @@ "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true @@ -42607,13 +55877,14 @@ "mode": "chat", "input_cost_per_token": 1.35e-07, "output_cost_per_token": 4e-07, - "max_input_tokens": 131072, - "max_output_tokens": 120000, - "max_tokens": 120000, + "max_input_tokens": 12288, + "max_output_tokens": 12288, + "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/qwen/qwen-2.5-72b-instruct": { "litellm_provider": "novita", @@ -42653,7 +55924,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528": { "litellm_provider": "novita", @@ -42693,7 +55965,8 @@ "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/microsoft/wizardlm-2-8x22b": { "litellm_provider": "novita", @@ -42703,7 +55976,8 @@ "max_input_tokens": 65535, "max_output_tokens": 8000, "max_tokens": 8000, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528-qwen3-8b": { "litellm_provider": "novita", @@ -42750,7 +56024,8 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "litellm_provider": "novita", @@ -42761,7 +56036,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "supports_vision": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-scout-17b-16e-instruct": { "litellm_provider": "novita", @@ -42897,7 +56173,9 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/google/gemma-3-27b-it": { "litellm_provider": "novita", @@ -42935,7 +56213,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/Sao10K/L3-8B-Stheno-v3.2": { "litellm_provider": "novita", @@ -43003,7 +56282,9 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true }, "novita/qwen/qwen3-vl-30b-a3b-instruct": { "litellm_provider": "novita", @@ -43124,10 +56405,12 @@ "input_cost_per_token": 3e-08, "output_cost_per_token": 3e-08, "max_input_tokens": 128000, - "max_output_tokens": 20000, - "max_tokens": 20000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/qwen/qwen2.5-7b-instruct": { "litellm_provider": "novita", @@ -43135,8 +56418,8 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 7e-08, "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -43586,31 +56869,15 @@ "/v1/audio/speech" ] }, - "gpt-4o-mini-tts-2025-03-20": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openai", - "mode": "audio_speech", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, - "output_cost_per_token": 1e-05, - "supported_endpoints": [ - "/v1/audio/speech" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ] - }, "gpt-4o-mini-tts-2025-12-15": { - "input_cost_per_token": 2.5e-06, + "deprecation_date": "2027-01-06", + "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_second": 0.00025, "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" ], @@ -43623,25 +56890,30 @@ ] }, "gpt-4o-mini-transcribe-2025-03-20": { + "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "gpt-4o-mini-transcribe-2025-12-15": { "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_second": 5e-05, "input_cost_per_token": 1.25e-06, "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -43655,6 +56927,12 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -43677,6 +56955,12 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -43689,45 +56973,13 @@ "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false }, - "gpt-realtime-mini-2025-10-06": { - "cache_creation_input_audio_token_cost": 3e-07, - "cache_read_input_audio_token_cost": 3e-07, - "cache_read_input_token_cost": 6e-08, - "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "realtime", - "output_cost_per_audio_token": 2e-05, - "output_cost_per_token": 2.4e-06, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-realtime-mini-2025-12-15": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_image_token_cost": 8e-08, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -43753,13 +57005,15 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2027-01-20", + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-realtime-whisper": { - "input_cost_per_second": 0.0002833333333333333, + "input_cost_per_second": 0.000283333333333, "litellm_provider": "openai", "mode": "audio_transcription", - "source": "https://platform.openai.com/docs/models/gpt-realtime-whisper", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -43773,10 +57027,11 @@ "supports_audio_input": true }, "sora-2": { + "deprecation_date": "2026-09-24", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, - "source": "https://platform.openai.com/docs/api-reference/videos", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" @@ -43786,10 +57041,11 @@ ] }, "sora-2-pro": { + "deprecation_date": "2026-09-24", "litellm_provider": "openai", "mode": "video_generation", "output_cost_per_video_per_second": 0.3, - "source": "https://platform.openai.com/docs/api-reference/videos", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" @@ -43800,9 +57056,10 @@ }, "sora-2-pro-high-res": { "litellm_provider": "openai", + "deprecation_date": "2026-09-24", "mode": "video_generation", "output_cost_per_video_per_second": 0.5, - "source": "https://platform.openai.com/docs/api-reference/videos", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "image" @@ -43812,12 +57069,20 @@ ] }, "chatgpt-image-latest": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_image_token": 1e-05, + "cache_read_input_token_cost_batches": 6.3e-07, + "deprecation_date": "2026-12-01", + "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "openai", "mode": "image_generation", - "output_cost_per_image_token": 4e-05, + "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -43865,52 +57130,17 @@ "tpm": 250000, "rpm": 10 }, - "gemini/gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-07, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-flash-native-audio-latest": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -43927,15 +57157,16 @@ "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-09-2025": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -43952,15 +57183,16 @@ "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-12-2025": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -43974,18 +57206,23 @@ ], "supports_audio_input": true, "supports_audio_output": true, - "gemini_native_audio": true + "gemini_native_audio": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true }, "gemini-3.1-flash-live-preview": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, + "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -44007,18 +57244,90 @@ "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05, + "supports_response_schema": false + }, + "gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_response_schema": false + }, + "gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true, + "supports_response_schema": false }, "gemini/gemini-2.5-flash-native-audio-latest": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -44037,15 +57346,16 @@ "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-09-2025": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -44064,15 +57374,16 @@ "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -44088,18 +57399,24 @@ "supports_audio_output": true, "tpm": 250000, "rpm": 10, - "gemini_native_audio": true + "gemini_native_audio": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-live-preview": { "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, "input_cost_per_video_per_second": 3.3333333333333335e-05, + "input_cost_per_video_token": 1e-06, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -44123,31 +57440,114 @@ "supports_web_search": true, "tpm": 250000, "rpm": 10, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "input_cost_per_second": 8.33333333333e-05, + "supports_response_schema": false, + "supports_reasoning": true }, - "gemini-2.5-flash-preview-tts": { - "input_cost_per_token": 3e-07, + "gemini/gemini-3.1-flash-tts-preview": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "audio_speech", - "output_cost_per_token": 2.5e-06, - "source": "https://ai.google.dev/pricing", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "tpm": 4000000, + "rpm": 10, + "supports_function_calling": false, + "supports_response_schema": false, + "supports_web_search": false + }, + "gemini/gemini-3.8-flash-tts": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 2.25e-07, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, + "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_token_batches": 4.5e-06, + "output_cost_per_token_flex": 4.5e-06, + "output_cost_per_token_priority": 1.62e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supports_prompt_caching": true + }, + "gemini/gemini-3.8-flash-lite-tts": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 2.25e-07, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, + "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 6e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_batches": 3e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.08e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supports_prompt_caching": true + }, + "gemini-2.5-flash-preview-tts": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supports_audio_input": false, + "supports_function_calling": false, + "supports_response_schema": false, + "supports_web_search": false }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -44176,24 +57576,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -44222,28 +57635,42 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -44267,28 +57694,45 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -44312,10 +57756,26 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, @@ -44364,16 +57824,21 @@ } }, "vertex_ai/claude-sonnet-5@default": { + "deprecation_date": "2026-12-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -44392,20 +57857,27 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6@default": { + "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -44422,7 +57894,8 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "duckduckgo/search": { "litellm_provider": "duckduckgo", @@ -44451,7 +57924,7 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-20b": { - "input_cost_per_token": 7.5e-08, + "input_cost_per_token": 7e-08, "output_cost_per_token": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, @@ -44485,8 +57958,8 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 65536, @@ -44501,17 +57974,27 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "cache_creation_input_token_cost": 6.875e-06, - "cache_read_input_token_cost": 5.5e-07, - "output_cost_per_token": 3.3e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012 + }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -44522,17 +58005,65 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html" }, "bedrock_mantle/openai.gpt-5.6-terra": { - "input_cost_per_token": 2.75e-06, - "cache_creation_input_token_cost": 3.4375e-06, - "cache_read_input_token_cost": 2.75e-07, - "output_cost_per_token": 1.65e-05, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "output_cost_per_token": 1.32e-05, + "output_cost_per_token_above_272k_tokens": 1.98e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012 + }, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html" + }, + "bedrock_mantle/openai.gpt-5.6-cyber": { + "input_cost_per_token": 1.375e-05, + "cache_creation_input_token_cost": 1.71875e-05, + "cache_read_input_token_cost": 1.375e-06, + "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -44550,19 +58081,25 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, - "bedrock_mantle/openai.gpt-5.6-luna": { - "input_cost_per_token": 1.1e-06, - "cache_creation_input_token_cost": 1.375e-06, - "cache_read_input_token_cost": 1.1e-07, - "output_cost_per_token": 6.6e-06, + "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": { + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -44578,23 +58115,826 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html" + }, + "bedrock_mantle/openai.gpt-5.6-luna": { + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_above_272k_tokens": 4.4e-07, + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, + "output_cost_per_token": 1.32e-06, + "output_cost_per_token_above_272k_tokens": 1.98e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012 + }, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" + }, + "us.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "global.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "us.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "output_cost_per_token": 1.32e-05, + "output_cost_per_token_above_272k_tokens": 1.98e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "global.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "us.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_above_272k_tokens": 4.4e-07, + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, + "output_cost_per_token": 1.32e-06, + "output_cost_per_token_above_272k_tokens": 1.98e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "us.openai.gpt-5.4": { + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "global.openai.gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "us.openai.gpt-5.5": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "global.openai.gpt-5.5": { + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "global.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "bedrock_mantle/openai.gpt-6-astra": { + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" + }, + "bedrock_mantle/openai.gpt-6-sol": { + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + }, + "bedrock_mantle/openai.gpt-6-luna": { + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_above_272k_tokens": 2.2e-07, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, + "cache_read_input_token_cost": 1.1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, + "output_cost_per_token": 5.5e-07, + "output_cost_per_token_above_272k_tokens": 8.25e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" + }, + "us.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "us.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "us.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_above_272k_tokens": 2.2e-07, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-07, + "cache_read_input_token_cost": 1.1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-08, + "output_cost_per_token": 5.5e-07, + "output_cost_per_token_above_272k_tokens": 8.25e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "global.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "openai.gpt-6-sol": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] + }, + "openai.gpt-6-luna": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "supports_sampling_params": false, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] }, "bedrock_mantle/openai.gpt-5.5": { "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012 + }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -44605,23 +58945,36 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html" }, "bedrock_mantle/openai.gpt-5.4": { "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.012, + "search_context_size_medium": 0.012 + }, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ @@ -44632,11 +58985,15 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html" }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, @@ -44700,11 +59057,17 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -44716,13 +59079,206 @@ "supports_vision": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock_mantle/xai.grok-4.6": { + "use_openai_responses_path": true, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 6.6e-06, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-6.html" + }, + "bedrock_mantle/anthropic.claude-haiku-4-5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5e-07, + "output_cost_per_token_batches": 2.5e-06 + }, + "bedrock_mantle/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "bedrock_mantle/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5-5.html" + }, + "us.xai.grok-4.6": { + "supports_regex_lookaround": false, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 6.6e-06, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "global.xai.grok-4.6": { + "supports_regex_lookaround": false, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-pro-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", + "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, @@ -44754,13 +59310,45 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-08, + "input_cost_per_token": 4.3125e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.15625e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", + "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, @@ -44798,7 +59386,7 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", + "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, @@ -44836,7 +59424,7 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://www.volcengine.com/docs/82379/1330310", + "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": false, @@ -44879,7 +59467,11 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-west-2/zai.glm-5": { @@ -44893,7 +59485,11 @@ "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, + "supports_native_structured_output": true, "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0": { @@ -44902,6 +59498,7 @@ "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -44927,6 +59524,7 @@ "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 1.2e-06, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, @@ -44959,10 +59557,12 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "prompt_cache_min_tokens": 1024 }, "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, @@ -44975,7 +59575,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { "max_tokens": 16384, @@ -44990,7 +59591,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { "max_tokens": 16384, @@ -45006,7 +59608,8 @@ "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, - "supports_response_schema": true + "supports_response_schema": true, + "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { "max_tokens": 16384, @@ -45021,7 +59624,8 @@ "supports_vision": true, "supports_prompt_caching": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { "max_tokens": 16384, @@ -45306,17 +59910,45 @@ "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" }, - "deepseek-v4-flash": { + "deepseek-flash": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 2.8e-09, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -45326,22 +59958,159 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true + }, + "deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepseek-v4-flash-vision-exp": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "deepseek", "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 8.7e-07, + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -45351,22 +60120,105 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false }, + "deepseek/deepseek-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 2.8e-09, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -45376,22 +60228,51 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "deepseek/deepseek-v4-pro": { + "deepseek/deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 8.7e-07, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -45401,6 +60282,61 @@ "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepseek/deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -45458,6 +60394,56 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/minimax-m3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.tencentcloud.com/products/tokenhub", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "cognition/swe-1.6": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "cognition", + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "source": "https://docs.devin.ai/windsurf/plugins/cascade/models" + }, + "cognition/swe-1.7": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "cognition", + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "source": "https://docs.devin.ai/desktop/models" + }, + "cognition/swe-1.7-lightning": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "litellm_provider": "cognition", + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "source": "https://docs.devin.ai/desktop/models" + }, "pinstripes/ps/glm-4.5-air": { "max_tokens": 128000, "max_input_tokens": 128000, @@ -45469,7 +60455,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { "max_tokens": 131072, @@ -45482,7 +60468,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { "max_tokens": 131072, @@ -45495,7 +60481,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { "max_tokens": 131072, @@ -45508,7 +60494,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": false, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { "max_tokens": 163840, @@ -45521,7 +60507,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": true, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { "max_tokens": 1000192, @@ -45534,7 +60520,7 @@ "supports_function_calling": true, "supports_assistant_prefill": true, "supports_reasoning": false, - "source": "https://pinstripes.io/pricing" + "source": "https://pinstripes.io/" }, "darkbloom/gemma-4-26b": { "input_cost_per_token": 3e-08, @@ -45570,6 +60556,411 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "xai/grok-4.20-0309-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-multi-agent-0309": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "xai/grok-build-0.1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "input_cost_per_token_above_200k_tokens": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "supports_response_schema": true, + "supports_vision": true + }, + "gpt-transcribe": { + "input_cost_per_second": 7.5e-05, + "litellm_provider": "openai", + "mode": "audio_transcription", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "gpt-live-transcribe": { + "input_cost_per_second": 0.000283333333333, + "litellm_provider": "openai", + "mode": "audio_transcription", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "gpt-live-1": { + "input_cost_per_second": 0.000833333333333, + "litellm_provider": "openai", + "mode": "realtime", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "gpt-realtime-translate": { + "input_cost_per_second": 0.000566666666667, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "max_tokens": 2000, + "mode": "realtime", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true + }, + "claude-mythos-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "prompt_cache_min_tokens": 512, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "provider_specific_entry": { + "us": 1.1 + } + }, + "claude-mythos-5-1": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" + }, + "claude-mythos-preview": { + "deprecation_date": "2026-06-09", + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "prompt_cache_min_tokens": 512, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/models/overview", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "provider_specific_entry": { + "us": 1.1 + } + }, + "gemini/gemini-robotics-er-2-streaming-preview": { + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014 + }, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "mistral/mistral-small-2603": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/labs-leanstral-1-5": { + "deprecation_date": "2026-09-30", + "input_cost_per_token": 0.0, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-moderation-2603": { + "input_cost_per_token": 0.0, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "mode": "moderation", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/models/model-cards/mistral-moderation-26-03" + }, + "mistral/voxtral-mini-2602": { + "input_cost_per_second": 5e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-transcribe-realtime-2602": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-tts-2603": { + "input_cost_per_character": 1.6e-05, + "litellm_provider": "mistral", + "mode": "audio_speech", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, "fallback_generalizations": { "rules": [ { @@ -45611,20 +61002,19086 @@ }, { "name": "claude-adaptive-thinking", - "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "description": "Claude at version 4.6 or higher, in any id shape that contains claude--: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Turns on adaptive thinking for new versions and new families with no code change.", + "pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.6 or higher, in any id shape that contains claude--: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.", "model_info": { "supports_adaptive_thinking": true } }, + { + "name": "claude-legacy-thinking", + "pattern": "claude-[a-z]+-4[-._]6(?!\\d)", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.6 exactly, in any id shape that contains claude--4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.", + "model_info": { + "supports_legacy_thinking": true + } + }, + { + "name": "claude-always-on-thinking", + "pattern": "claude-(?:fable|mythos)-", + "description": "Any Claude Fable or Mythos id, under any provider namespace and any version. These families always think and reject thinking.type=disabled with a 400; the Anthropic transformations omit the param instead, so the model falls back to its default adaptive thinking.", + "model_info": { + "thinking_always_on": true + } + }, { "name": "claude-mid-conversation-system", - "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|(?:[5-9]|[1-9]\\d)(?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "description": "Claude at version 4.8 or higher, in any id shape that contains claude--: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.", + "pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.8 or higher, in any id shape that contains claude--: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.", "model_info": { "supports_mid_conversation_system": true } + }, + { + "name": "claude-tool-search", + "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", + "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.", + "model_info": { + "supports_tool_search": true + } + }, + { + "name": "wandb-reasoning-baseline", + "pattern": "^wandb/", + "description": "Any Weights & Biases Inference model id, anchored to the wandb/ namespace so only that provider's ids match. W&B's serverless catalog is reasoning-first and grows faster than this registry names it, so an id the map has not described yet is treated as reasoning-capable and keeps the caller's reasoning_effort instead of dropping it or raising UnsupportedParamsError. Rules lose to exact entries, so a mapped non-reasoning model such as wandb/meta-llama/Llama-3.1-8B-Instruct is unaffected. Carries no mode and no pricing, so cost stays on the standard unpriced behavior and the deployment does not read as catalog-mapped to the router's reasoning-effort resolver.", + "model_info": { + "supports_reasoning": true + } + }, + { + "name": "openai-reasoning-family-baseline", + "pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))", + "fill_missing_for_providers": ["azure", "azure_ai", "openai"], + "description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.", + "model_info": { + "supports_reasoning": true + } + }, + { + "name": "gemini-chat-baseline", + "pattern": "gemini-(?!.*(?:-tts|-image|-live|-audio|-embedding|-computer-use|-robotics|-transcribe|-translate))(?:2[.-][5-9]|[3-9](?:[.-]\\d{1,2})?)-(?:pro|flash)(?:-lite)?(?![a-z])", + "description": "Any Gemini text-chat id at 2.5 or higher under any namespace, including bare ids, gemini/, vertex_ai/, openrouter/google/, deepinfra/google/, vercel_ai_gateway/google/, oci/google., and databricks-gemini--: gemini-[.minor]-(pro|flash)[-lite] with any trailing preview, date or variant tag. The capability flags were verified against each of those providers' own catalogs and docs. The lookahead excludes the tts, image, live, audio, embedding, computer-use, robotics, transcribe and translate lines, which are different modes with different capabilities. Provider-specific deviations, such as Perplexity's Agent API serving these as mode responses, are carried by their exact map entries, which always win over this rule. Carries no token limits or pricing, so those stay on the standard unmapped behavior rather than a guessed number. Source check 2026-09-15: all 45 first-party 2.5+ text-chat entries in this map carry every field below, and the OpenRouter (openrouter.ai/api/v1/models), Vercel AI Gateway (ai-gateway.vercel.sh/v1/models), DeepInfra (api.deepinfra.com/models/list), OCI and Databricks model docs list reasoning, tools and image input for the same models.", + "model_info": { + "mode": "chat", + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_response_schema": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + } } ] + }, + "gemini/gemini-3.5-live-translate-preview": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_token": 3.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 2.1e-05, + "output_cost_per_token": 2.1e-05, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_response_schema": false, + "supports_web_search": false, + "tpm": 250000 + }, + "gemini/gemini-3.5-transcribe": { + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "gemini", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "audio_transcription", + "output_cost_per_token": 1.2e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "tpm": 800000, + "rpm": 2000, + "supports_function_calling": false + }, + "gemini/gemini-3.5-transcribe-live": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_token": 3.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "audio_transcription", + "output_cost_per_token": 2.1e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, + "supports_function_calling": false + }, + "vertex_ai/gemini-3.5-transcribe-preview": { + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "vertex_ai/gemini-3.5-transcribe-live-preview": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_token": 3.5e-06, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 2.1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "vertex_ai/gemini-3.5-live-translate-preview": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_second": 8.83333333333e-05, + "input_cost_per_token": 3.5e-06, + "litellm_provider": "vertex_ai", + "mode": "realtime", + "output_cost_per_audio_token": 2.1e-05, + "output_cost_per_token": 2.1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "audio", + "text" + ], + "supports_audio_input": true, + "supports_audio_output": true + }, + "perplexity/pplx-embed-context-v1-0.6b": { + "input_cost_per_token": 8e-09, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.perplexity.ai/getting-started/pricing" + }, + "perplexity/pplx-embed-context-v1-4b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560, + "source": "https://docs.perplexity.ai/getting-started/pricing" + }, + "voyage/voyage-4-large": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/voyage-4": { + "input_cost_per_token": 6e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/voyage-4-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/voyage-code-4": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/voyage-context-4": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 120000, + "max_tokens": 120000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/voyage-multimodal-3.5": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing", + "supports_embedding_image_input": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_response_schema": true + }, + "fireworks_ai/accounts/fireworks/models/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/deepseek-v4p1-flash": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/deepseek-v4p1-flash-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_response_schema": true + }, + "fireworks_ai/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p2-fast-us": { + "cache_read_input_token_cost": 2.1e-07, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/kimi-k3-fast": { + "cache_read_input_token_cost": 4.5e-07, + "input_cost_per_token": 4.5e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/kimi-k3-us": { + "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, + "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/qwen3p8-max": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "output_cost_per_token_priority": 2.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/nemotron-3-ultra-nvfp4": { + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "output_cost_per_token_priority": 2.5e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/qwen3p8-max": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_priority": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us": { + "cache_read_input_token_cost": 2.1e-07, + "deprecation_date": "2026-09-25", + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/kimi-k3-fast": { + "cache_read_input_token_cost": 4.5e-07, + "input_cost_per_token": 4.5e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/kimi-k3-us": { + "cache_read_input_token_cost": 4.5e-07, + "cache_read_input_token_cost_priority": 5.625e-07, + "input_cost_per_token": 4.5e-06, + "input_cost_per_token_priority": 5.625e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.25e-05, + "output_cost_per_token_priority": 2.8125e-05, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 1.3200000000000002e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/tencent/hy3": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.499999999999999e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-venti": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.35e-07, + "input_cost_per_token": 1.6000000000000001e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/inclusionai/ling-3.0-flash-fast": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/inclusionai/ling-3.0-flash": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-tall": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4.5000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/stepfun/step-3.7-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5.0000000000000004e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.0000000000000002e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/baidu/cobuddy": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "novita", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.13e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5": { + "cache_read_input_token_cost": 3.4e-09, + "input_cost_per_token": 1.6800000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.3600000000000004e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.7-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5-pro": { + "cache_read_input_token_cost": 4.3e-09, + "input_cost_per_token": 5.22e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.044e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-27b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 8.000000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.38e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7-highspeed": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.5-highspeed": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.5-27b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-122b-a10b": { + "input_cost_per_token": 4.0000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-35b-a3b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-397b-a17b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/minimax/minimax-m2.5": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5": { + "cache_read_input_token_cost": 2.0000000000000002e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3-coder-next": { + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-ocr-2": { + "input_cost_per_token": 3e-08, + "litellm_provider": "novita", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://novita.ai/pricing", + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 1.0000000000000001e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-4.7-h": { + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-4.7-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 7e-08, + "litellm_provider": "novita", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.48e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.4850000000000002e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek_v3": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v3/community": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1/community": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/thudm/glm-4-32b-0414": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.66e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "novita", + "max_input_tokens": 131000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2e-08, + "source": "https://api.novita.ai/v3/openai/models", + "supports_response_schema": true, + "supports_vision": false + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash": { + "supports_reasoning": true, + "max_tokens": 1048576, + "max_input_tokens": 1049000, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "deprecation_date": "2026-10-05", + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Pro": { + "supports_reasoning": true, + "max_tokens": 1048576, + "max_input_tokens": 1049000, + "input_cost_per_token": 1.15e-06, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-10-05", + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/google/gemma-4-31B-it": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/ibm-granite/granite-4.1-8b": { + "deprecation_date": "2026-10-05", + "max_tokens": 131072, + "max_input_tokens": 131000, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "deprecation_date": "2026-10-05", + "max_tokens": 131072, + "max_input_tokens": 131000, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "deprecation_date": "2026-10-05", + "max_tokens": 128000, + "max_input_tokens": 131000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/MiniMaxAI/MiniMax-M3": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 9.6e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.7-Code": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.6": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3.41e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.15e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/OpenPipe/Qwen3-14B-Instruct": { + "deprecation_date": "2026-10-05", + "max_tokens": 32768, + "max_input_tokens": 32800, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.2e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.8-27B": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-35B-A3B": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-27B": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 1.2e-07, + "deprecation_date": "2026-10-05", + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.5-35B-A3B": { + "deprecation_date": "2026-10-05", + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "deprecation_date": "2026-10-05", + "max_tokens": 262144, + "max_input_tokens": 262000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Pro-0813": { + "litellm_provider": "wandb", + "mode": "chat", + "supports_reasoning": true, + "input_cost_per_token": 1.31e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "max_input_tokens": 1049000, + "supports_prompt_caching": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/ibm-granite/granite-4.2-8b": { + "litellm_provider": "wandb", + "mode": "chat", + "supports_reasoning": true, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 5e-08, + "max_input_tokens": 131000, + "supports_prompt_caching": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/zai-org/GLM-5.2": { + "supports_reasoning": true, + "max_tokens": 262144, + "max_input_tokens": 1049000, + "input_cost_per_token": 7.6e-07, + "output_cost_per_token": 2.42e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "deepinfra/openai/gpt-oss-120b-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 7.6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 2.25e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7-Flash": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 1e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.6": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-8": { + "input_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepinfra/anthropic/claude-sonnet-4-6": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "prompt_cache_min_tokens": 1024, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_adaptive_thinking": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-turbo": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/thinkingmachines/Inkling-Small": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/meta-models/Muse-Glimmer-30B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max-Thinking": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8.8e-07, + "cache_read_input_token_cost": 1.1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 2.6e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-5": { + "input_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepinfra/thinkingmachines/Inkling": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4.05e-06, + "cache_read_input_token_cost": 1.6e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.7-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-mini": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M3": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 2.8e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 5.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-flash-lite": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true + }, + "deepinfra/google/gemini-3.7-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true + }, + "deepinfra/inclusionAI/Ling-3.0-flash": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/stepfun-ai/Step-3.7-Flash": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-1.8": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/tencent/Hy3": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.8e-07, + "cache_read_input_token_cost": 3.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-code": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-pro": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.08e-06, + "cache_read_input_token_cost": 1.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6.8e-07, + "output_cost_per_token": 3.4e-06, + "cache_read_input_token_cost": 1.36e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepinfra/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-E4B-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V3.2": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 3.8e-07, + "cache_read_input_token_cost": 1.3e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "cache_read_input_token_cost": 2.06e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-122B-A10B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.9e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 1.05e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 2.05e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 8.5e-08, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 2.85e-06, + "output_cost_per_token": 1.425e-05, + "cache_read_input_token_cost": 2.85e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-7": { + "input_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 2048, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "deepinfra/Qwen/Qwen3.6-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-26B-A4B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-pro": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-haiku-4-5": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "prompt_cache_min_tokens": 4096, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/openai/gpt-oss-120b-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-9B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.7e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.75e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "gemini/gemini-omni-1.1-flash": { + "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "rpm": 2000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_audio_input": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "tpm": 800000 + }, + "xai/grok-4.20": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-imagine-image": { + "input_cost_per_image": 0.02, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-2026-03-02": { + "input_cost_per_image": 0.02, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-quality": { + "deprecation_date": "2026-11-02", + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-quality-20260403": { + "deprecation_date": "2026-11-02", + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-quality-latest": { + "deprecation_date": "2026-11-02", + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-pro": { + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-image-2.0": { + "input_cost_per_image": 0.06, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-imagine-video": { + "input_cost_per_image": 0.002, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.05, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.07, + "source": "https://docs.x.ai/docs/models/grok-imagine-video", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] + }, + "xai/grok-imagine-video-1.5": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "xai/grok-imagine-video-1.5-lite": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://docs.x.ai/developers/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "xai/grok-imagine-video-1.5-2026-05-30": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "xai/grok-imagine-video-1.5-preview": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.08, + "output_cost_per_second_1080p": 0.25, + "output_cost_per_second_480p": 0.08, + "output_cost_per_second_720p": 0.14, + "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5", + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ] + }, + "xai/grok-voice-transcribe-1.0": { + "deprecation_date": "2026-10-02", + "input_cost_per_second": 2.778e-05, + "litellm_provider": "xai", + "metadata": { + "calculation": "$0.10/3600 seconds = $0.00002778 per second", + "original_pricing_per_hour": 0.1 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "xai/grok-voice-transcribe-2.0": { + "input_cost_per_second": 2.778e-05, + "litellm_provider": "xai", + "metadata": { + "calculation": "$0.10/3600 seconds = $0.00002778 per second", + "original_pricing_per_hour": 0.1 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "low/1024-x-1024/grok-imagine-image-2.0": { + "input_cost_per_image": 0.04, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "xai/grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-non-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-multi-agent": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-multi-agent-latest": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "groq/qwen/qwen3.8-27b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-medium-3.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-vibe-cli-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-vibe-cli-with-tools": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-vibe-cli-fast": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-code-latest": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-code-fim-latest": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-code-agent-latest": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/devstral-2-vibe-cli", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-ocr-3": { + "litellm_provider": "mistral", + "ocr_cost_per_page": 0.002, + "ocr_cost_per_page_batches": 0.001, + "annotation_cost_per_page": 0.003, + "annotation_cost_per_page_batches": 0.0015, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ], + "source": "https://mistral.ai/pricing#api-pricing" + }, + "mistral/mistral-ocr-3-0": { + "litellm_provider": "mistral", + "ocr_cost_per_page": 0.002, + "ocr_cost_per_page_batches": 0.001, + "annotation_cost_per_page": 0.003, + "annotation_cost_per_page_batches": 0.0015, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ], + "source": "https://mistral.ai/pricing#api-pricing" + }, + "mistral/mistral-ocr-4": { + "annotation_cost_per_page": 0.005, + "annotation_cost_per_page_batches": 0.0025, + "litellm_provider": "mistral", + "mode": "ocr", + "ocr_cost_per_page": 0.004, + "ocr_cost_per_page_batches": 0.002, + "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", + "supported_endpoints": [ + "/v1/ocr", + "/v1/batch" + ] + }, + "mistral/voxtral-mini-latest": { + "input_cost_per_second": 5e-05, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-realtime-2602": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-realtime-latest": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/labs-leanstral-1-5-1": { + "input_cost_per_token": 0.0, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-5p3": { + "cache_read_input_token_cost": 2.6e-07, + "cache_read_input_token_cost_priority": 3.25e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, + "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3": { + "cache_read_input_token_cost": 2.6e-07, + "cache_read_input_token_cost_priority": 3.25e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_priority": 1.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_priority": 5.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-us": { + "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, + "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/routers/auto": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/auto-instant": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/firerouter": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/glm-5p3-flash": { + "cache_read_input_token_cost": 3e-08, + "cache_read_input_token_cost_priority": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 1.875e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_priority": 6.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/glm-5p3-flash-us": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/inkling": { + "cache_read_input_token_cost": 1.7e-07, + "cache_read_input_token_cost_priority": 1.7e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_priority": 1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.05e-06, + "output_cost_per_token_priority": 4.05e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "embedding", + "source": "https://api.fireworks.ai/v1/serverless/models" + }, + "zai/glm-5.2": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "zai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.z.ai/guides/overview/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3.8-Flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.82e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/moonshotai/Kimi-K2.5-fp4": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.8e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "together_ai/MiniMaxAI/MiniMax-M2.7": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 6e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 196608, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 7e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 163840, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "deprecation_date": "2026-02-25", + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, + "cerebras/gemma-4-31b": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 131072, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 1.49e-06, + "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "elevenlabs/scribe_v2": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://elevenlabs.io/pricing/api", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "scaleway/glm-5.2": { + "input_cost_per_token": 1.8e-06, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": false + }, + "scaleway/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure_ai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "deprecation_date": "2026-10-03", + "input_cost_per_token": 9.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "deprecation_date": "2026-12-15", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" + }, + "azure_ai/MAI-Image-2.6": { + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "mode": "image_generation", + "output_cost_per_image_token": 3.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure_ai/MAI-Image-2.6-Flash": { + "input_cost_per_image_token": 2.5e-06, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "mode": "image_generation", + "output_cost_per_image_token": 1.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ] + }, + "azure_ai/FW-DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.1e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5.3": { + "cache_read_input_token_cost": 3.25e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GLM-5.3-Flash": { + "cache_read_input_token_cost": 3.8e-08, + "input_cost_per_token": 1.88e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/FW-GPT-OSS-120B": { + "deprecation_date": "2027-07-01", + "cache_read_input_token_cost": 8.2e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "azure_ai/Cohere-command-a-plus-05-2026": { + "deprecation_date": "2026-10-16", + "input_cost_per_token": 8e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-medium-3-5": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_response_schema": true, + "supports_vision": true + }, + "azure_ai/deepseek-r1": { + "deprecation_date": "2026-08-13", + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3-0324": { + "deprecation_date": "2026-07-13", + "input_cost_per_token": 1.14e-06, + "output_cost_per_token": 4.56e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3.1": { + "deprecation_date": "2026-07-13", + "input_cost_per_token": 1.23e-06, + "output_cost_per_token": 4.94e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3": { + "deprecation_date": "2026-05-01", + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3-mini": { + "deprecation_date": "2026-05-01", + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.27e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-non-reasoning": { + "deprecation_date": "2026-05-01", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-reasoning": { + "deprecation_date": "2026-05-01", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true + }, + "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 8.4e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock/us-gov-west-1/anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_1hr": 2.4e-05, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.2e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512 + }, + "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 262144, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.88e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_system_messages": true, + "supports_vision": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true + }, + "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.76e-07, + "supports_system_messages": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false + }, + "bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 8.4e-08, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock/us-gov-east-1/anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-east-1/anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-east-1/anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 7.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.2e-05, + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-east-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "bedrock/us-gov-east-1/anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_1hr": 2.4e-05, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.2e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512 + }, + "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "input_cost_per_token": 2.64e-06, + "input_cost_per_token_above_272k_tokens": 5.28e-06, + "cache_creation_input_token_cost": 3.3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, + "cache_read_input_token_cost": 2.64e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, + "output_cost_per_token": 1.584e-05, + "output_cost_per_token_above_272k_tokens": 2.376e-05 + }, + "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "input_cost_per_token": 2.64e-07, + "input_cost_per_token_above_272k_tokens": 5.28e-07, + "cache_creation_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, + "cache_read_input_token_cost": 2.64e-08, + "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, + "output_cost_per_token": 1.584e-06, + "output_cost_per_token_above_272k_tokens": 2.376e-06 + }, + "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "input_cost_per_token": 3.3e-06, + "cache_read_input_token_cost": 3.3e-07, + "output_cost_per_token": 1.98e-05 + }, + "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { + "use_openai_responses_path": true, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://aws.amazon.com/bedrock/pricing/", + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2.4e-07 + }, + "bedrock_mantle/us-gov-west-1/xai.grok-4.6": { + "use_openai_responses_path": true, + "input_cost_per_token": 2.64e-06, + "output_cost_per_token": 7.92e-06, + "cache_read_input_token_cost": 6.6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/google.gemma-4-e2b": { + "input_cost_per_token": 4.8e-08, + "output_cost_per_token": 9.6e-08, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b": { + "input_cost_per_token": 1.56e-07, + "output_cost_per_token": 4.8e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/google.gemma-4-31b": { + "input_cost_per_token": 1.68e-07, + "output_cost_per_token": 4.8e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b": { + "input_cost_per_token": 8.4e-08, + "output_cost_per_token": 3.6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html" + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5-5.html" + }, + "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, + "supports_vision": true, + "input_cost_per_token": 3.3e-06, + "cache_read_input_token_cost": 3.3e-07, + "output_cost_per_token": 1.98e-05 + }, + "bedrock_mantle/us-gov-east-1/xai.grok-4.6": { + "use_openai_responses_path": true, + "input_cost_per_token": 2.64e-06, + "output_cost_per_token": 7.92e-06, + "cache_read_input_token_cost": 6.6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b": { + "input_cost_per_token": 8.4e-08, + "output_cost_per_token": 3.6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/deepseek.v3.1": { + "input_cost_per_token": 5.8e-07, + "output_cost_per_token": 1.68e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + }, + "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + }, + "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 8.8e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + }, + "bedrock_mantle/qwen.qwen3-32b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 32000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + }, + "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + }, + "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 5.3e-07, + "output_cost_per_token": 2.66e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + }, + "azure/us-gov/gpt-5.1": { + "cache_read_input_token_cost": 1.71875e-07, + "default_reasoning_effort": "none", + "input_cost_per_token": 1.71875e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.375e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us-gov/o3-mini": { + "cache_read_input_token_cost": 7.57e-07, + "input_cost_per_token": 1.513e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.05e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/us-gov/text-embedding-3-large": { + "input_cost_per_token": 1.63e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/us-gov/text-embedding-3-small": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "cloudflare/@cf/openai/whisper": { + "input_cost_per_second": 7.5e-06, + "litellm_provider": "cloudflare", + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "rpm": 720, + "source": "https://developers.cloudflare.com/workers-ai/models/whisper/", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "cloudflare/@cf/openai/whisper-large-v3-turbo": { + "input_cost_per_second": 8.5e-06, + "litellm_provider": "cloudflare", + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "rpm": 720, + "source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gemini/lyria-3.5-clip-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_image": 0.04, + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false + }, + "gemini/lyria-3.5-pro-preview": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "output_cost_per_image": 0.08 + }, + "gemini/lyria-3.5": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "output_cost_per_image": 0.08 + }, + "gemini/lyria-realtime-exp": { + "input_cost_per_token": 0, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_function_calling": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_web_search": false, + "output_cost_per_image": 0.08 + }, + "perplexity/anthropic/claude-fable-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-4-8": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "cache_read_input_token_cost": 5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-sonnet-4-6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-terra": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_above_272k_tokens": 4e-07, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_above_272k_tokens": 5e-06, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-mini": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.4-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "cache_read_input_token_cost": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-pro-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.1-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "cache_read_input_token_cost": 2.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.5-flash-lite": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.6-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.7-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.6": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-non-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.20-multi-agent": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/glm-5.3-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 3e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3.5-lightning-30b-a3b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "supports_reasoning": true, + "input_cost_per_token": 1.15e-08, + "output_cost_per_token": 1.7e-07, + "cache_read_input_token_cost": 1.15e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_function_calling": true, + "supports_reasoning": true, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "openrouter/anthropic/claude-fable-5": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1e-06, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "prompt_cache_min_tokens": 512, + "supports_web_search": true + }, + "openrouter/anthropic/claude-fable-5.1": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "prompt_cache_min_tokens": 512, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.8": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "supports_web_search": true + }, + "openrouter/google/gemini-2.5-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 3e-08, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1e-08, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 3e-07, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 3e-07, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_audio_token": 3e-06, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_audio_token": 3e-07, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.6-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 7.5e-07, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.7-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 7.5e-07, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.8-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 7.5e-07, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.1": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.25e-07, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.3-codex": { + "input_cost_per_token": 1.75e-06, + "output_cost_per_token": 1.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 1.75e-07, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "input_cost_per_token_above_272k_tokens": 5e-06, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4-mini": { + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-08, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4-nano": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.5": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "input_cost_per_token_above_272k_tokens": 4e-07, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-luna-pro": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-terra-pro": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/o3": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/o4-mini": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.75e-07, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4.20": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4.20-multi-agent": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4.3": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4.5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4.6": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-build-0.1": { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token_above_200k_tokens": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "baseten/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/zai-org/GLM-5.3-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/minimax/minimax-m3": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6e-08, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.7-plus": { + "input_cost_per_token": 3.2e-07, + "input_cost_per_token_above_256k_tokens": 9.6e-07, + "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.92e-07, + "output_cost_per_token_above_256k_tokens": 3.84e-06, + "output_cost_per_token": 1.28e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6.4e-08, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 4e-07, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-6-astra": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-astra-pro": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/qwen/qwen3.8-flash": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.7e-07, + "cache_read_input_token_cost": 1.6e-08, + "cache_creation_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.3-flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-flash-vision-exp": { + "input_cost_per_token": 2.156e-07, + "output_cost_per_token": 6.468e-07, + "cache_read_input_token_cost": 6.86e-09, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.3": { + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.8-27b": { + "cache_creation_input_token_cost": 5.3125e-07, + "input_cost_per_token": 4.25e-07, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 8.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3.5-lightning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.8-max": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/qwen/qwen3.8-max", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true + }, + "openrouter/qwen/qwen3.8-max-0902": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.8-max-prime": { + "input_cost_per_token": 4e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_video_input": true, + "supports_prompt_caching": true + }, + "openrouter/deepseek/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 1.52e-08, + "input_cost_per_token": 1.52e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 1.28e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.7-flash": { + "input_cost_per_token": 3e-08, + "input_cost_per_token_above_32k_tokens": 1e-07, + "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07, + "cache_read_input_token_cost_above_32k_tokens": 2e-08, + "output_cost_per_token_above_32k_tokens": 4e-07, + "output_cost_per_token": 1.3e-07, + "cache_read_input_token_cost": 6e-09, + "cache_creation_input_token_cost": 3.8e-08, + "input_cost_per_token_above_256k_tokens": 2e-07, + "output_cost_per_token_above_256k_tokens": 8e-07, + "cache_read_input_token_cost_above_256k_tokens": 4e-08, + "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/poolside/laguna-s-2.1": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 9e-09, + "deprecation_date": "2026-10-31", + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/poolside/laguna-s-2.1:free": { + "deprecation_date": "2026-10-31", + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 7e-07, + "input_cost_per_token": 7.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/poolside/laguna-xs-2.1": { + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-31", + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/poolside/laguna-xs-2.1:free": { + "deprecation_date": "2026-10-31", + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/google/gemini-3.1-flash-lite-image": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-image": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3-pro-image": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 2e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/z-ai/glm-5.2": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1.04e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.2:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 6.712e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 3.35e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3.5-content-safety": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3.5-content-safety:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m3:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/qwen/qwen3.7-max": { + "input_cost_per_token": 1.475e-06, + "output_cost_per_token": 4.425e-06, + "cache_read_input_token_cost": 2.95e-07, + "cache_creation_input_token_cost": 1.84375e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3-5": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.5-plus-20260420": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.8e-06, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_token_above_256k_tokens": 3.75e-07, + "output_cost_per_token_above_256k_tokens": 2.25e-06, + "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.6-flash": { + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 1.125e-06, + "cache_creation_input_token_cost": 2.34375e-07, + "input_cost_per_token_above_256k_tokens": 7.5e-07, + "output_cost_per_token_above_256k_tokens": 3e-06, + "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.6-max-preview": { + "cache_creation_input_token_cost": 1.28375e-06, + "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.027e-06, + "input_cost_per_token_above_128k_tokens": 1.58e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6.162e-06, + "output_cost_per_token_above_128k_tokens": 9.48e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.6-27b": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 81920, + "max_tokens": 81920, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true + }, + "openrouter/openai/gpt-chat-latest": { + "input_cost_per_token": 5e-06, + "output_cost_per_token": 3e-05, + "cache_read_input_token_cost": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/deepseek/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.24e-08, + "input_cost_per_token": 2.24e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 1.28e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-26b-a4b-it": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 6.75e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 2.25e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-26b-a4b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-31b-it": { + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-31b-it:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5v-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "deprecation_date": "2098-12-31", + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.7": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 2.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 176947, + "max_tokens": 176947, + "mode": "chat", + "output_cost_per_token": 8.4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.7:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 196608, + "max_output_tokens": 176947, + "max_tokens": 176947, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/mistralai/mistral-small-2603": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5-turbo": { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2.4e-07, + "deprecation_date": "2098-12-31", + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 4.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.5-9b": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/gpt-5.4-pro": { + "input_cost_per_token": 3e-05, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 6e-05, + "output_cost_per_token_above_272k_tokens": 0.00027, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-image-preview": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "output_cost_per_image_token": 6e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-pro-preview-customtools": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 2e-07, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/qwen/qwen3-max-thinking": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 7.8e-07, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "input_cost_per_token_above_32k_tokens": 1.56e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.9e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "output_cost_per_token_above_32k_tokens": 7.8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-coder-next": { + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 8e-07, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2-her": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-audio": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "input_cost_per_audio_token": 3.2e-05, + "output_cost_per_audio_token": 6.4e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-audio-mini": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.4e-06, + "input_cost_per_audio_token": 6e-07, + "output_cost_per_audio_token": 2.4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.6v": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/google/gemini-3-pro-image-preview": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 2e-07, + "input_cost_per_audio_token": 2e-06, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.1-codex": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.1-codex-mini": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/mistralai/voxtral-small-24b-2507": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_audio_token": 0.0001, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.75e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-vl-32b-instruct": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.04e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.16e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-vl-8b-thinking": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-vl-8b-instruct": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.17e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.55e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemini-2.5-flash-image": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.5e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 8.33333333333333e-08, + "cache_read_input_audio_token_cost": 1e-07, + "deprecation_date": "2027-03-15", + "input_cost_per_audio_token": 1e-06, + "output_cost_per_image_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": true + }, + "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/gpt-5-pro": { + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true + }, + "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 2.1e-07, + "output_cost_per_token": 1.9e-06, + "cache_read_input_token_cost": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-max": { + "cache_creation_input_token_cost": 9.75e-07, + "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, + "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06, + "cache_read_input_token_cost": 1.56e-07, + "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, + "cache_read_input_token_cost_above_32k_tokens": 3.12e-07, + "deprecation_date": "2026-10-09", + "input_cost_per_token": 7.8e-07, + "input_cost_per_token_above_128k_tokens": 1.95e-06, + "input_cost_per_token_above_32k_tokens": 1.56e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.9e-06, + "output_cost_per_token_above_128k_tokens": 9.75e-06, + "output_cost_per_token_above_32k_tokens": 7.8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v3.1-terminus": { + "cache_read_input_token_cost": 1.35e-07, + "deprecation_date": "2026-09-28", + "input_cost_per_token": 2.7e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 147456, + "max_tokens": 147456, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-coder-flash": { + "input_cost_per_token": 1.95e-07, + "input_cost_per_token_above_32k_tokens": 3.25e-07, + "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07, + "cache_read_input_token_cost_above_32k_tokens": 6.5e-08, + "output_cost_per_token_above_32k_tokens": 1.625e-06, + "output_cost_per_token": 9.75e-07, + "cache_read_input_token_cost": 3.9e-08, + "cache_creation_input_token_cost": 2.4375e-07, + "input_cost_per_token_above_128k_tokens": 5.2e-07, + "output_cost_per_token_above_128k_tokens": 2.6e-06, + "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, + "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-next-80b-a3b-thinking": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen-plus-2025-07-28": { + "cache_creation_input_token_cost": 3.25e-07, + "cache_read_input_token_cost": 5.2e-08, + "deprecation_date": "2026-10-09", + "input_cost_per_token": 2.6e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2-0905": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 81920, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3.1": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.5v": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 1.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/mistralai/codestral-2508": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 9e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { + "input_cost_per_token": 4.815e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.9305e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.5": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1.1e-07, + "deprecation_date": "2026-12-31", + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.5-air": { + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 8.5e-07, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2": { + "input_cost_per_token": 5.7e-07, + "output_cost_per_token": 2.3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m1": { + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2.2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/o3-pro": { + "input_cost_per_token": 2e-05, + "output_cost_per_token": 8e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true + }, + "openrouter/google/gemini-2.5-pro-preview": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 1.25e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/google/gemini-2.5-pro-preview-05-06": { + "input_cost_per_token": 1.25e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost": 3.75e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/meta-llama/llama-guard-4-12b": { + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-30b-a3b": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-8b": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.17e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.55e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-14b": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-32b": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3-235b-a22b": { + "deprecation_date": "2026-10-09", + "input_cost_per_token": 4.55e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.82e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/o4-mini-high": { + "input_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/meta-llama/llama-4-maverick": { + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 6.525e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-4-scout": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/o1-pro": { + "input_cost_per_token": 0.00015, + "output_cost_per_token": 0.0006, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true + }, + "openrouter/google/gemma-3-4b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-3-27b-it": { + "input_cost_per_token": 8e-08, + "output_cost_per_token": 4.5e-07, + "cache_read_input_token_cost": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-saba": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen2.5-vl-72b-instruct": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen-plus": { + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 7.8e-07, + "cache_read_input_token_cost": 5.2e-08, + "cache_creation_input_token_cost": 3.25e-07, + "input_cost_per_token_above_256k_tokens": 7.8e-07, + "output_cost_per_token_above_256k_tokens": 2.34e-06, + "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, + "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-24b-instruct-2501": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-r1-distill-llama-70b": { + "deprecation_date": "2026-09-28", + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-01": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000192, + "max_output_tokens": 900172, + "max_tokens": 900172, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.3-70b-instruct": { + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-4o-2024-11-20": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false + }, + "openrouter/mistralai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen-2.5-7b-instruct": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2.7e-08, + "output_cost_per_token": 2.01e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 60000, + "max_output_tokens": 54000, + "max_tokens": 54000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.2-3b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 3.3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen-2.5-72b-instruct": { + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-4o-2024-08-06": { + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false + }, + "openrouter/meta-llama/llama-3.1-70b-instruct": { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.1-8b-instruct": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "cache_read_input_token_cost": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-nemo": { + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-4o-mini-2024-07-18": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false + }, + "openrouter/google/gemma-2-27b-it": { + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "together_ai/arcee-ai/trinity-mini": { + "input_cost_per_token": 4.5e-08, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 128000, + "max_tokens": 128000 + }, + "vertex_ai/gemini-2.5-flash-native-audio": { + "deprecation_date": "2026-12-13", + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 3e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, + "litellm_provider": "vertex_ai", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.5-flash-preview-tts": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.1-flash-tts-preview": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.5-transcribe": { + "input_cost_per_audio_token": 2e-06, + "input_cost_per_second": 5e-05, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.5-transcribe-live": { + "input_cost_per_audio_token": 3.5e-06, + "input_cost_per_second": 8.33333333333e-05, + "litellm_provider": "vertex_ai", + "mode": "audio_transcription", + "output_cost_per_token": 2.1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-omni-1.1-flash": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-omni-1.1-flash-preview": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_output_tokens": 57920, + "max_tokens": 57920, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_reasoning": true, + "supports_video_input": true, + "supports_vision": true + }, + "vertex_ai/gemma-4-26b-a4b-it": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "gpt-5.5-cyber": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true + }, + "gpt-rosalind-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "together_ai/meta-llama/Llama-3.1-405B-Instruct": { + "input_cost_per_token": 3.5e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 4096, + "max_tokens": 4096 + }, + "together_ai/meta-llama/Llama-3.2-1B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 + }, + "together_ai/Qwen/Qwen2-1.5B-Instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-08, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 + }, + "together_ai/Qwen/Qwen2.5-14B-Instruct": { + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 + }, + "together_ai/Salesforce/Llama-Rank-V1": { + "deprecation_date": "2026-02-06", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-07, + "source": "https://api.together.xyz/v1/models" + }, + "together_ai/together/Tev1-4B-experimental": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/QwQ-32B": { + "deprecation_date": "2025-11-13", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "deprecation_date": "2026-02-06", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", + "input_cost_per_token": 1.95e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "deprecation_date": "2026-06-04", + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", + "input_cost_per_token": 5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "deprecation_date": "2026-04-02", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "deprecation_date": "2026-02-25", + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", + "input_cost_per_token": 5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen3.5-397B-A17B": { + "cache_read_input_token_cost": 3.5e-07, + "deprecation_date": "2026-06-29", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", + "input_cost_per_token": 1.6e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-05-14", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/google/gemma-4-31B-it": { + "deprecation_date": "2026-09-15", + "input_cost_per_token": 3.9e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-02-06", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "deprecation_date": "2026-02-25", + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "deprecation_date": "2026-03-06", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "deprecation_date": "2025-11-13", + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "deprecation_date": "2026-04-02", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "deprecation_date": "2026-04-16", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-19", + "input_cost_per_token": 1.2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.9e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token": 9.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 512288, + "max_tokens": 512288, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/openai/gpt-oss-20b": { + "deprecation_date": "2026-09-15", + "input_cost_per_token": 5e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "deprecation_date": "2026-04-02", + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/zai-org/GLM-4.7": { + "deprecation_date": "2026-04-02", + "input_cost_per_token": 4.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/zai-org/GLM-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "deprecation_date": "2026-07-10", + "input_cost_per_token": 1.4e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 202752, + "max_tokens": 202752, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.together.ai/v1/models" + }, + "azure/eu/codex-mini": { + "deprecation_date": "2026-11-15", + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-05-13": { + "deprecation_date": "2026-12-09", + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_batches": 1.375e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 5.5e-09, + "cache_read_input_token_cost_batches": 2.75e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2": { + "deprecation_date": "2027-06-08", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_batches": 9.625e-08, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_batches": 4.125e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_batches": 1.1e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-6-astra": { + "deprecation_date": "2028-01-11", + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'swedencentral'%20and%20priceType%20eq%20'Consumption'", + "supports_reasoning": true + }, + "azure/eu/gpt-6-luna": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 3e-07, + "cache_read_input_token_cost": 1.2e-08, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-08, + "input_cost_per_token": 1.2e-07, + "input_cost_per_token_above_272k_tokens": 2.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_272k_tokens": 9e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/eu/gpt-6-sol": { + "deprecation_date": "2028-03-11", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 4.8e-07, + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-2025-04-16": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o4-mini-2025-04-16": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-large": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-small": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_token": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true, + "supports_reasoning": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_token": 1e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "tpm": 250000, + "rpm": 10, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true, + "supports_reasoning": true + }, + "azure/us/codex-mini": { + "deprecation_date": "2026-11-15", + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4o-2024-05-13": { + "deprecation_date": "2026-12-09", + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_batches": 6.875e-08, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_batches": 1.375e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 5.5e-09, + "cache_read_input_token_cost_batches": 2.75e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "deprecation_date": "2027-06-08", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_batches": 9.625e-08, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_batches": 4.125e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 2.2e-08, + "cache_read_input_token_cost_batches": 1.1e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "responses", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-realtime-2": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2026-10-31", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-live-1": { + "deprecation_date": "2027-09-10", + "input_cost_per_second": 0.000833333333333, + "litellm_provider": "azure", + "mode": "realtime", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "azure/gpt-live-transcribe": { + "deprecation_date": "2028-02-01", + "input_cost_per_second": 0.000283333333333, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "audio_transcription", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "azure/gpt-transcribe": { + "deprecation_date": "2028-02-01", + "input_cost_per_second": 7.5e-05, + "litellm_provider": "azure", + "mode": "audio_transcription", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/audio/transcriptions", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "azure/gpt-realtime-translate": { + "deprecation_date": "2027-05-06", + "input_cost_per_second": 0.000566666666667, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true + }, + "aihubmix/agnes-2.5-flash": { + "input_cost_per_token": 3e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 512000, + "max_output_tokens": 65500, + "max_tokens": 65500, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/agnes-2.5-pro": { + "cache_read_input_token_cost": 3.78e-09, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/cc-glm-5.1": { + "input_cost_per_token": 6e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/claude-fable-5": { + "cache_read_input_token_cost": 1.1e-06, + "cache_creation_input_token_cost": 1.375e-05, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_sampling_params": false + }, + "aihubmix/claude-haiku-4-5": { + "cache_read_input_token_cost": 1.1e-07, + "cache_creation_input_token_cost": 1.375e-06, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5.5e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096 + }, + "aihubmix/claude-opus-4-8-think": { + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 6.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false + }, + "aihubmix/claude-opus-5": { + "cache_read_input_token_cost": 5e-07, + "cache_creation_input_token_cost": 6.25e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_sampling_params": false + }, + "aihubmix/claude-sonnet-5": { + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 2.5e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false + }, + "aihubmix/coding-glm-5.3": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/coding-kimi-k3": { + "cache_read_input_token_cost": 6.6e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.61333e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/coding-xiaomi-mimo-v2-omni": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 8e-08, + "litellm_provider": "aihubmix", + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/coding-xiaomi-mimo-v2.5": { + "cache_read_input_token_cost": 1.6e-09, + "input_cost_per_token": 8e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/coding-xiaomi-mimo-v2.5-pro": { + "cache_read_input_token_cost": 1.6e-09, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/command-a-plus-05-2026": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.84e-08, + "input_cost_per_token": 1.42e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.84e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.4027e-07, + "input_cost_per_token": 1.69e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.38e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/doubao-seed-2-0-code-preview": { + "cache_read_input_token_cost": 9.644e-08, + "input_cost_per_token": 4.822e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.411e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/doubao-seed-2-0-lite-260428": { + "cache_read_input_token_cost": 1.8082e-08, + "input_cost_per_token": 9.041e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.4246e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/doubao-seed-2-0-mini": { + "cache_read_input_token_cost": 6.027e-09, + "input_cost_per_token": 3.0136e-08, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.0136e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/doubao-seed-2-0-pro": { + "cache_read_input_token_cost": 9.644e-08, + "input_cost_per_token": 4.822e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.411e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/doubao-seed-2-1-turbo": { + "cache_read_input_token_cost": 9.295e-08, + "input_cost_per_token": 4.6475e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.32375e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/ernie-5.1": { + "cache_read_input_token_cost": 5.634e-07, + "input_cost_per_token": 5.634e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 119000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.5353e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "aihubmix/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemini-3-flash-preview-search": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.499999e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 3.9998e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 3.9998e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/glm-5.2-fast-preview": { + "cache_read_input_token_cost": 5.635e-07, + "input_cost_per_token": 2.254e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.889e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/glm-5.3": { + "cache_read_input_token_cost": 2.817e-07, + "input_cost_per_token": 1.1268e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.9438e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/glm-5.3-flash": { + "cache_read_input_token_cost": 2.817e-08, + "input_cost_per_token": 1.1268e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.9438e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/glm-5v-turbo": { + "cache_read_input_token_cost": 1.69008e-07, + "input_cost_per_token": 7.042e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.09848e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/gpt-5.4-high": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.4-low": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.5-pro": { + "input_cost_per_token": 3e-05, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00018, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/gpt-5.6-luna": { + "cache_read_input_token_cost": 2e-08, + "cache_creation_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/gpt-5.6-sol-disc": { + "cache_read_input_token_cost": 4e-07, + "cache_creation_input_token_cost": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/gpt-5.6-terra": { + "cache_read_input_token_cost": 2e-07, + "cache_creation_input_token_cost": 2.5e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/grok-4-20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/grok-4-20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/grok-build-0.1": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/hy3": { + "cache_read_input_token_cost": 3.905e-08, + "input_cost_per_token": 1.562e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.248e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/hy4-preview": { + "cache_read_input_token_cost": 4.225e-08, + "input_cost_per_token": 8.45e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.535e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/kimi-k2.6": { + "cache_read_input_token_cost": 1.60835e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.9995e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.2167e-07, + "input_cost_per_token": 1.9e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.999e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/longcat-2.0": { + "cache_read_input_token_cost": 1.5492e-08, + "input_cost_per_token": 7.746e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.0984e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "aihubmix/mai-thinking-1": { + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/mimo-v2-omni": { + "cache_read_input_token_cost": 8.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/mimo-v2-pro": { + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 3.3e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_web_search": true + }, + "aihubmix/minimax-m2.7": { + "cache_read_input_token_cost": 5.916e-08, + "input_cost_per_token": 2.958e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 1.1832e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/minimax-m3": { + "input_cost_per_token": 2.88e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.152e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/muse-spark-1.2": { + "input_cost_per_token": 1.375e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.675e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/qwen3-coder-next": { + "input_cost_per_token": 1.37e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5.48e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_response_schema": true + }, + "aihubmix/qwen3.5-122b-a10b": { + "input_cost_per_token": 1.126e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9.008e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.5-397b-a17b": { + "input_cost_per_token": 1.644e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9.864e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-27b": { + "input_cost_per_token": 4.22e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.532e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.54e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.524e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-max-preview": { + "cache_read_input_token_cost": 1.268e-07, + "cache_creation_input_token_cost": 1.585e-06, + "input_cost_per_token": 1.268e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.608e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/qwen3.7-plus": { + "cache_read_input_token_cost": 5.64e-08, + "cache_creation_input_token_cost": 3.525e-07, + "input_cost_per_token": 2.82e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.128e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-2.4t-a95b": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-flash": { + "cache_read_input_token_cost": 1.4075e-08, + "cache_creation_input_token_cost": 1.75937e-07, + "input_cost_per_token": 1.126e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.80025e-07, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-max": { + "cache_read_input_token_cost": 1.69e-07, + "cache_creation_input_token_cost": 2.1125e-06, + "input_cost_per_token": 1.69e-06, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.07e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/step-3.7-flash": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 2.2e-07, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "openrouter/typesafe/jev-1.13": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 32000, + "max_output_tokens": 28800, + "max_tokens": 28800, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/typesafe/jev-1.13" + }, + "openrouter/typesafe/jev-router": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://openrouter.ai/typesafe/jev-router", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "bespoke/nimble-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "bespoke/nimble": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://ollama.com/library/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately" + } + }, + "bespoke/bespokelabs/Bespoke-Nimble-9B": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/english": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/multilingual": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/typed-decisions": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "strands_decider/strands-decider-2B-hobson-v19": { + "input_cost_per_token": 0.0, + "litellm_provider": "strands_decider", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "typesafe/jev-1.13.0": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models" + }, + "typesafe/jev-latest": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models" + }, + "typesafe/jev-preview": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models" + }, + "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "source": "https://wandb.ai/site/pricing/tokens/", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "wandb/google/gemma-4-26B-A4B-it": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "max_input_tokens": 262000, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://wandb.ai/site/pricing/tokens/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://docs.wandb.ai/inference/models.md", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/~anthropic/claude-fable-latest": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~anthropic/claude-haiku-latest": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~anthropic/claude-opus-latest": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~anthropic/claude-sonnet-latest": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~deepseek/deepseek-flash-latest": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/~deepseek/deepseek-pro-latest": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, + "output_cost_per_token": 3.96e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/~deepseek/deepseek-v4-flash-latest": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/~google/gemini-flash-latest": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 7.5e-08, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 7.5e-07, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~google/gemini-pro-latest": { + "cache_creation_input_token_cost": 3.75e-07, + "cache_read_input_audio_token_cost": 2e-07, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~moonshotai/kimi-latest": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/~openai/gpt-astra-latest": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~openai/gpt-luna-latest": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~openai/gpt-mini-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~openai/gpt-sol-latest": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~openai/gpt-terra-latest": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~x-ai/grok-latest": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/~z-ai/glm-flash-latest": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/~z-ai/glm-latest": { + "cache_read_input_token_cost": 1.2142e-07, + "input_cost_per_token": 6.538e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.0548e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-2.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.0": { + "cache_read_input_token_cost": 7.5e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.0-mini": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 7e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.5": { + "cache_read_input_token_cost": 7.5e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.5-mini": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 7e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-rp-llama-3.1-8b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/amazon/nova-2-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-lite-v1": { + "input_cost_per_token": 6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 300000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-micro-v1": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/amazon/nova-premier-v1": { + "cache_read_input_token_cost": 6.25e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-pro-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 300000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/anthracite-org/magnum-v4-72b": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/anthropic/claude-fable-5:batch": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-fable-5.1:batch": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-haiku-4.5:batch": { + "cache_creation_input_token_cost": 6.25e-07, + "cache_creation_input_token_cost_above_1hr": 1e-06, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.1:batch": { + "cache_creation_input_token_cost": 9.375e-06, + "cache_creation_input_token_cost_above_1hr": 1.5e-05, + "cache_read_input_token_cost": 7.5e-07, + "input_cost_per_token": 7.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3.75e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.5:batch": { + "cache_creation_input_token_cost": 3.125e-06, + "cache_creation_input_token_cost_above_1hr": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.6:batch": { + "cache_creation_input_token_cost": 3.125e-06, + "cache_creation_input_token_cost_above_1hr": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.7:batch": { + "cache_creation_input_token_cost": 3.125e-06, + "cache_creation_input_token_cost_above_1hr": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.8:batch": { + "cache_creation_input_token_cost": 3.125e-06, + "cache_creation_input_token_cost_above_1hr": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-5:batch": { + "cache_creation_input_token_cost": 3.125e-06, + "cache_creation_input_token_cost_above_1hr": 5e-06, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.5:batch": { + "cache_creation_input_token_cost": 1.875e-06, + "cache_creation_input_token_cost_above_1hr": 3e-06, + "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06, + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_above_200k_tokens": 3e-07, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_above_200k_tokens": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_above_200k_tokens": 1.125e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.6:batch": { + "cache_creation_input_token_cost": 1.875e-06, + "cache_creation_input_token_cost_above_1hr": 3e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-5:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/arcee-ai/trinity-large-thinking": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 80000, + "max_tokens": 80000, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/baidu/ernie-4.5-vl-424b-a47b": { + "deprecation_date": "2026-10-08", + "input_cost_per_token": 4.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 123000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-1.6": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_above_128k_tokens": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_128k_tokens": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-1.6-flash": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2-1-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-code": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 5e-07, + "input_cost_per_token_above_128k_tokens": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "output_cost_per_token_above_128k_tokens": 6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-lite": { + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_above_128k_tokens": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_128k_tokens": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-mini": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_128k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_above_128k_tokens": 8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-a": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r-08-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r-plus-08-2024": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r7b-12-2024": { + "input_cost_per_token": 3.75e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/north-mini-code:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/apodex/apodex-1.1-mini:free": { + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/unbiased/pareto-26.10-preview": { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 3.2e-06, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/dots-studio/dots-3-note-preview:free": { + "deprecation_date": "2026-12-31", + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 512000, + "max_output_tokens": 460800, + "max_tokens": 460800, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemini-2.5-flash-lite:batch": { + "cache_read_input_audio_token_cost": 3e-08, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_audio_token": 1.5e-07, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-flash:batch": { + "cache_read_input_audio_token_cost": 1e-07, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-pro:batch": { + "cache_read_input_audio_token_cost": 1.25e-07, + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 6.25e-07, + "input_cost_per_token": 6.25e-07, + "input_cost_per_token_above_200k_tokens": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_200k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3-flash-preview:batch": { + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.1-flash-lite:batch": { + "cache_read_input_audio_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1.25e-08, + "input_cost_per_audio_token": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.1-pro-preview:batch": { + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 9e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash-lite:batch": { + "cache_read_input_audio_token_cost": 1.5e-08, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_audio_token": 1.5e-07, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash:batch": { + "cache_read_input_audio_token_cost": 1.5e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1.5e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.6-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 3.75e-08, + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 3.75e-07, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.7-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 3.75e-08, + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 3.75e-07, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.8-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-08, + "cache_read_input_audio_token_cost": 3.75e-08, + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 3.75e-07, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/ibm-granite/granite-4.0-h-micro": { + "input_cost_per_token": 1.7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131000, + "max_output_tokens": 117900, + "max_tokens": 117900, + "mode": "chat", + "output_cost_per_token": 1.12e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/ibm-granite/granite-4.2-8b": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inception/mercury-2": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 50000, + "max_tokens": 50000, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inception/mercury-2.5": { + "cache_read_input_token_cost": 4e-09, + "input_cost_per_token": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.3e-08, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-fin": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.232e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-fin:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-sante:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-vl": { + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 2.1e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.16e-08, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-vl:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/inference-net/schematron-v2-small": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.3e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inference-net/schematron-v2-turbo": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/kwaipilot/kat-coder-pro-v2.5": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 7.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 2.96e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/liquid/lfm-2.5-2.6b:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meituan/longcat-2.0": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048756, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta/muse-spark-1.1": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.2": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.2-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.3": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.3-contributor": { + "cache_read_input_token_cost": 2e-09, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/microsoft/phi-4": { + "input_cost_per_token": 7e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 16384, + "max_output_tokens": 14745, + "max_tokens": 14745, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/microsoft/wizardlm-2-8x22b": { + "input_cost_per_token": 6.2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65535, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 6.2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/codestral-2508:batch": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/ministral-8b-2512:batch": { + "cache_read_input_token_cost": 7.5e-09, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 7.5e-08, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-large-2512": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-large-2512:batch": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3-5:batch": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3.1:batch": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-2603:batch": { + "cache_read_input_token_cost": 7.5e-09, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k3:batch": { + "cache_read_input_token_cost": 2.28e-07, + "input_cost_per_token": 2.28e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.14e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 81920, + "max_output_tokens": 38000, + "max_tokens": 38000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/nex-agi/nex-n2.5-mini:free": { + "deprecation_date": "2026-09-25", + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nex-agi/nex-n2.5-pro:free": { + "deprecation_date": "2026-09-25", + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nousresearch/hermes-3-llama-3.1-405b": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/nousresearch/hermes-3-llama-3.1-70b": { + "input_cost_per_token": 7e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/nousresearch/hermes-4-405b": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-3.5-turbo-0613": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-3.5-turbo:batch": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": true + }, + "openrouter/openai/gpt-4-turbo:batch": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-4.1-mini:batch": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-4.1-nano:batch": { + "cache_read_input_token_cost": 1.25e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-4.1:batch": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-4o-mini:batch": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-4o:batch": { + "cache_read_input_token_cost": 6.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5-image": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5-image-mini": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5-mini:batch": { + "cache_read_input_token_cost": 1.25e-08, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5-nano:batch": { + "cache_read_input_token_cost": 2.5e-09, + "input_cost_per_token": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5-pro:batch": { + "input_cost_per_token": 7.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5:batch": { + "cache_read_input_token_cost": 6.25e-08, + "input_cost_per_token": 6.25e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.1:batch": { + "cache_read_input_token_cost": 6.25e-08, + "input_cost_per_token": 6.25e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.2-pro:batch": { + "input_cost_per_token": 1.05e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8.4e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.2:batch": { + "cache_read_input_token_cost": 8.75e-08, + "input_cost_per_token": 8.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4-image-2": { + "cache_read_input_token_cost": 2e-06, + "input_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-image-2": { + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://openrouter.ai/api/v1/images/models/openai/gpt-image-2/endpoints", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "openrouter/openai/gpt-image-2.5-flare": { + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://openrouter.ai/api/v1/images/models/openai/gpt-image-2.5-flare/endpoints", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "openrouter/openai/gpt-image-2.5-sunburst": { + "input_cost_per_image_token": 8e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "source": "https://openrouter.ai/api/v1/images/models/openai/gpt-image-2.5-sunburst/endpoints", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supports_vision": true + }, + "openrouter/openai/gpt-5.4-mini:batch": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 3.75e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4-nano:batch": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.25e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4-pro:batch": { + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_above_272k_tokens": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-05, + "output_cost_per_token_above_272k_tokens": 0.000135, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.4:batch": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_272k_tokens": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_above_272k_tokens": 1.125e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.5-pro:batch": { + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_above_272k_tokens": 3e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-05, + "output_cost_per_token_above_272k_tokens": 0.000135, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.5:batch": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-luna-pro:batch": { + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_272k_tokens": 9e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-luna:batch": { + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_272k_tokens": 9e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-sol-pro:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-sol:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-terra-pro:batch": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-5.6-terra:batch": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-astra-pro:batch": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_above_272k_tokens": 3.75e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-astra:batch": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "output_cost_per_token_above_272k_tokens": 3.75e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/o3-mini:batch": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 5.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": true + }, + "openrouter/openai/o3:batch": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/o4-mini:batch": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 5.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perceptron/perceptron-mk1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 127072, + "max_output_tokens": 114364, + "max_tokens": 114364, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-deep-research": { + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-pro-search": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/qwen/qwen3.8-27b:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/rekaai/reka-edge": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 16384, + "max_output_tokens": 14745, + "max_tokens": 14745, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/rekaai/reka-flash-3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/relace/relace-apply-3": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/relace/relace-search": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/sakana/fugu-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/sakana/fugu-ultra": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/sakana/fugu-ultra-v2": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/sakana/sakana-namazu": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/sao10k/l3-lunaris-8b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, + "mode": "chat", + "output_cost_per_token": 5e-08, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/sao10k/l3.1-euryale-70b": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/sao10k/l3.3-euryale-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/stealth/space-bunny-alpha": { + "deprecation_date": "2026-10-05", + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "openrouter/stepfun/step-3.5-flash": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/stepfun/step-3.7-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 230400, + "max_tokens": 230400, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/tencent/hunyuan-a13b-instruct": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 5.7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy-mt2-1.8b": { + "input_cost_per_token": 4.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.77e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy-mt2-30b-a3b": { + "input_cost_per_token": 7.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.95e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy-mt2-7b": { + "input_cost_per_token": 7.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.95e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy3": { + "cache_read_input_token_cost": 3.3e-08, + "input_cost_per_token": 1.32e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8}, + "output_cost_per_token": 5.28e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy3-preview": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy4-preview": { + "cache_read_input_token_cost": 4.2e-08, + "input_cost_per_token": 8.34e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "off_peak_pricing": {"input_cost_per_token":7.506e-7,"output_cost_per_token":0.0000022509,"cache_read_input_token_cost":3.78e-8,"hours_utc":"16:00-00:00"}, + "output_cost_per_token": 2.501e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/thedrummer/cydonia-24b-v4.1": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/thedrummer/skyfall-36b-v2": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 5.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/thedrummer/unslopnemo-12b": { + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1024000, + "max_output_tokens": 819200, + "max_tokens": 819200, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 524288, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.05e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/thinkingmachines/inkling-small": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 524288, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/thinkingmachines/inkling-small:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/thinkingmachines/inkling:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/unbiased/pareto": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/upstage/solar-pro-3": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/upstage/solar-pro4": { + "cache_read_input_token_cost": 1.8e-08, + "input_cost_per_token": 9e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 524288, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.6e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/upstage/solar-mini4": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 524288, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/writer/palmyra-x5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1040000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/x-ai/grok-4.3:batch": { + "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_above_200k_tokens": 3.2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/z-ai/glm-5.3-flash:batch": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.3:batch": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/prism-ml/ternary-bonsai-2-27b": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.3-prime": { + "cache_read_input_token_cost": 5.6e-07, + "input_cost_per_token": 2.8e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-5.3-flashx": { + "cache_read_input_token_cost": 9e-08, + "deprecation_date": "2098-12-31", + "input_cost_per_token": 3.7e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/x-ai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "global.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_flex": 1.875e-06, + "cache_creation_input_token_cost_priority": 6.5625e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_flex": 1.5e-07, + "cache_read_input_token_cost_priority": 5.25e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_flex": 1.5e-06, + "input_cost_per_token_priority": 5.25e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_flex": 7.5e-06, + "output_cost_per_token_priority": 2.625e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/xiaomi/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/xiaomi/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": { + "cache_read_input_token_cost": 3.6e-08, + "input_cost_per_token": 4.35e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "xiaomi_mimo/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 4.35e-07, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "xiaomi_mimo/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "xai/grok-4.20-0309": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-beta": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-0309": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-latest-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-latest-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-beta-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-0304": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-0304-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-0304-reasoning": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-non-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-experimental-beta-reasoning-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "xai/grok-4.20-multi-agent-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "xai/grok-4.20-multi-agent-experimental-beta-0304": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "xai/grok-4.20-multi-agent-experimental-beta-latest": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "responses", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true, + "supported_endpoints": [ + "/v1/responses" + ] + }, + "xai/grok-4.20-non-reasoning-gv2": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_response_schema": true + }, + "xai/grok-4.20-reasoning-gv2": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "xai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1.25e-06, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "openrouter/nex-agi/nex-n2.5-mini": { + "cache_read_input_token_cost": 2.5e-09, + "input_cost_per_token": 2.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/nex-agi/nex-n2.5-pro": { + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 9.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.05e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/thinkingmachines/inkling-small": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.6e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.32e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/zai-org/GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.1e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_200k_tokens": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_above_200k_tokens": 4e-06, + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token": 1.2e-06, + "input_cost_per_token_priority": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.2e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { + "cache_read_input_token_cost_priority": 6e-07, + "deprecation_date": "2026-08-27", + "input_cost_per_token_priority": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "max_tokens": 196608, + "mode": "chat", + "output_cost_per_token_priority": 1.2e-06, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/ember-1": { + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-opus-5.5:batch": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/cohere/command-a-plus": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 192000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4.1-flash:batch": { + "cache_read_input_token_cost": 3.36e-09, + "input_cost_per_token": 1.12e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.36e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/openai/gpt-6-luna-pro:batch": { + "cache_creation_input_token_cost": 6.25e-08, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, + "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_above_272k_tokens": 1e-08, + "input_cost_per_token": 5e-08, + "input_cost_per_token_above_272k_tokens": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "output_cost_per_token_above_272k_tokens": 3.75e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-luna:batch": { + "cache_creation_input_token_cost": 6.25e-08, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, + "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_above_272k_tokens": 1e-08, + "input_cost_per_token": 5e-08, + "input_cost_per_token_above_272k_tokens": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "output_cost_per_token_above_272k_tokens": 3.75e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol-pro:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6-sol:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-oss-20b:batch": { + "input_cost_per_token": 2.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 1.12e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/perceptron/perceptron-mk1.5": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 36864, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "vertex_ai/gemini-2.0-flash": { + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_character": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.0-flash-lite": { + "deprecation_date": "2026-06-01", + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, + "input_cost_per_character": 1.875e-08, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_batches": 3.75e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/zai-org/glm-5.2-maas": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": ["global"], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-3.3-70b-instruct-maas": { + "deprecation_date": "2026-10-21", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/veo-3.0-generate-001": { + "deprecation_date": "2026-06-30", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-fast-generate-001": { + "deprecation_date": "2026-06-30", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.1, + "output_cost_per_second_1080p": 0.12, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-2.0-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.5, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/virtual-try-on-001": { + "deprecation_date": "2027-03-15", + "litellm_provider": "vertex_ai", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_modalities": [ + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, + "vertex_ai/gemini-2.5-flash-tts": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1e-05, + "output_cost_per_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.5-pro-tts": { + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "audio_speech", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "output_cost_per_token": 5e-05, + "input_cost_per_token": 1e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "global.anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_read_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_creation_input_token_cost_above_1hr": 2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "us.anthropic.claude-mythos-5-1": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "input_cost_per_token": 1.1e-05, + "output_cost_per_token": 5.5e-05, + "cache_read_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "us.anthropic.claude-mythos-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost": 1.375e-05, + "input_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 1.1e-06, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-fable-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "au.anthropic.claude-fable-5": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "output_cost_per_token": 5.5e-05, + "cache_creation_input_token_cost": 1.375e-05, + "cache_read_input_token_cost": 1.1e-06, + "input_cost_per_token": 1.1e-05, + "cache_creation_input_token_cost_above_1hr": 2.2e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-opus-4-7": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 2048, + "output_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 6.875e-06, + "input_cost_per_token": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_read_input_token_cost": 5.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "input_cost_per_token": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "output_cost_per_token": 2.75e-05, + "cache_read_input_token_cost": 5.5e-07, + "cache_creation_input_token_cost": 6.875e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 1.1e-05, + "cache_creation_input_token_cost": 6.875e-06, + "input_cost_per_token": 5.5e-06, + "cache_read_input_token_cost": 5.5e-07, + "output_cost_per_token": 2.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "input_cost_per_token": 4.4e-06, + "output_cost_per_token": 2.2e-05, + "cache_read_input_token_cost": 2.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-sonnet-4-6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "output_cost_per_token": 1.65e-05, + "cache_creation_input_token_cost_above_1hr": 6.6e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06, + "input_cost_per_token": 3.3e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 2.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "us.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "thinking_always_on": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_output_config": true, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "input_cost_per_token": 2.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "thinking_always_on": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_output_config": true, + "input_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "au.anthropic.claude-mythos-preview": { + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "thinking_always_on": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_output_config": true, + "input_cost_per_token": 2.75e-05, + "cache_creation_input_token_cost": 3.4375e-05, + "output_cost_per_token": 0.0001375, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "deepseek.r1-v1:0": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false + }, + "mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "azure_ai/MAI-Cyber-1-Flash": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-ocr-2505": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.001, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" + }, + "azure_ai/mistral-ocr-2512": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" + }, + "anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 2.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "au.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "azure_ai/claude-sonnet-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512 + }, + "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "eu.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "jp.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "openrouter/anthropic/claude-sonnet-5.5": { + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "supports_web_search": true + }, + "perplexity/anthropic/claude-sonnet-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-fable-5-1": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6.1-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_272k_tokens": 2e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.8-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.7": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "vertex_ai/claude-sonnet-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-sonnet-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "prism/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "prism/deepseek-v4-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "global.xai.grok-4.7": { + "supports_regex_lookaround": false, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.xai.grok-4.7": { + "supports_regex_lookaround": false, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "xai.grok-4.7": { + "supports_regex_lookaround": false, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-sonnet-5.5:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "global.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "bedrock_mantle/openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true + }, + "us.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "vertex_ai/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 6e-06, + "output_cost_per_token": 6e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/xai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/inclusionai/ling-3.1-flash": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "azure_ai/kimi-k2-thinking": { + "deprecation_date": "2026-03-29", + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": false, + "supports_vision": false } } diff --git a/tests/documentation_tests/test_env_keys.py b/tests/documentation_tests/test_env_keys.py index 60fbd505d67..e659cfe8c1f 100644 --- a/tests/documentation_tests/test_env_keys.py +++ b/tests/documentation_tests/test_env_keys.py @@ -28,6 +28,7 @@ EXCLUDED_GUARD_ONLY_VARS = { # environment settings docs until the feature is ready for broad use. EXCLUDED_ROLLOUT_FLAGS = { "LITELLM_USE_RUST_OCR", + "LITELLM_USE_LEGACY_INTERACTIONS_SCHEMA", } EXCLUDED_TERMINAL_VARS = {