From bdd4c8e564d640931852d4f4d20c51f34a7e0768 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 20 Aug 2026 19:14:11 +0000 Subject: [PATCH] fix(model_prices): add Gemini live-translate, Voyage 4 series, Perplexity contextualized embeddings; absorb Fireworks + Bedrock batch registry PRs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 508 +++++++++++++++++- model_prices_and_context_window.json | 508 +++++++++++++++++- .../test_bedrock_batch_pricing.py | 43 ++ 3 files changed, 1011 insertions(+), 48 deletions(-) create mode 100644 tests/test_litellm/test_bedrock_batch_pricing.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a2c51f9b952..d67309aebe7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -759,7 +759,9 @@ "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, @@ -2487,7 +2489,9 @@ "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 }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -2743,7 +2747,9 @@ "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 }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { "deprecation_date": "2026-07-30", @@ -2839,7 +2845,9 @@ "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 }, "azure/ada": { "input_cost_per_token": 1e-07, @@ -12452,7 +12460,9 @@ "supports_tool_choice": true, "supports_vision": 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 }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -17032,7 +17042,9 @@ "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, @@ -17255,7 +17267,9 @@ "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 }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-07, @@ -19861,7 +19875,7 @@ "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "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, @@ -19900,7 +19914,7 @@ "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": { @@ -19908,7 +19922,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -21593,7 +21612,7 @@ "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, + "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, @@ -21635,7 +21654,7 @@ "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": { @@ -21643,7 +21662,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -21995,7 +22019,7 @@ "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, + "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, @@ -22035,7 +22059,7 @@ "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": { @@ -22043,7 +22067,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -23373,7 +23402,9 @@ "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 }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -23431,7 +23462,9 @@ "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, @@ -28335,7 +28368,9 @@ "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 }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -28361,7 +28396,9 @@ "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, @@ -35163,7 +35200,9 @@ "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, @@ -37360,7 +37399,9 @@ "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, @@ -37526,7 +37567,9 @@ "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 }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -37581,7 +37624,9 @@ "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-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -49274,5 +49319,420 @@ } } ] + }, + "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", + "mode": "chat", + "output_cost_per_audio_token": 2.1e-05, + "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": [ + "audio" + ], + "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": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-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/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-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, + "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/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-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/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "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, + "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, + "input_cost_per_token": 3e-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, + "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-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, + "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": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "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, + "input_cost_per_token": 2e-06, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "output_cost_per_token": 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": true + }, + "fireworks_ai/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-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, + "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/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-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, + "input_cost_per_token": 6e-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, + "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/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-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, + "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/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-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, + "input_cost_per_token": 6e-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, + "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/qwen3p8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "output_cost_per_token": 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": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "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/glm-5p2-fast-us": { + "cache_read_input_token_cost": 2.1e-07, + "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, + "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/accounts/fireworks/routers/kimi-k3-us": { + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "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 } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a2c51f9b952..d67309aebe7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -759,7 +759,9 @@ "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, @@ -2487,7 +2489,9 @@ "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 }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -2743,7 +2747,9 @@ "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 }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { "deprecation_date": "2026-07-30", @@ -2839,7 +2845,9 @@ "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 }, "azure/ada": { "input_cost_per_token": 1e-07, @@ -12452,7 +12460,9 @@ "supports_tool_choice": true, "supports_vision": 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 }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, @@ -17032,7 +17042,9 @@ "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, @@ -17255,7 +17267,9 @@ "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 }, "eu.meta.llama3-2-1b-instruct-v1:0": { "input_cost_per_token": 1.3e-07, @@ -19861,7 +19875,7 @@ "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-07, "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, @@ -19900,7 +19914,7 @@ "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": { @@ -19908,7 +19922,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -21593,7 +21612,7 @@ "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, + "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, @@ -21635,7 +21654,7 @@ "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": { @@ -21643,7 +21662,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -21995,7 +22019,7 @@ "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, + "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, @@ -22035,7 +22059,7 @@ "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": { @@ -22043,7 +22067,12 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "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, @@ -23373,7 +23402,9 @@ "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 }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -23431,7 +23462,9 @@ "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, @@ -28335,7 +28368,9 @@ "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 }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -28361,7 +28396,9 @@ "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, @@ -35163,7 +35200,9 @@ "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, @@ -37360,7 +37399,9 @@ "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, @@ -37526,7 +37567,9 @@ "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 }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -37581,7 +37624,9 @@ "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-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -49274,5 +49319,420 @@ } } ] + }, + "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", + "mode": "chat", + "output_cost_per_audio_token": 2.1e-05, + "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": [ + "audio" + ], + "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": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-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/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-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, + "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/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-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/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "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, + "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, + "input_cost_per_token": 3e-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, + "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-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, + "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": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "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, + "input_cost_per_token": 2e-06, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "output_cost_per_token": 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": true + }, + "fireworks_ai/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-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, + "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/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-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, + "input_cost_per_token": 6e-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, + "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/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 3.5e-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, + "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/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-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, + "input_cost_per_token": 6e-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, + "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/qwen3p8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "fireworks_ai", + "mode": "chat", + "output_cost_per_token": 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": true + }, + "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast": { + "cache_read_input_token_cost": 2.1e-07, + "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/glm-5p2-fast-us": { + "cache_read_input_token_cost": 2.1e-07, + "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, + "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/accounts/fireworks/routers/kimi-k3-us": { + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "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 } } diff --git a/tests/test_litellm/test_bedrock_batch_pricing.py b/tests/test_litellm/test_bedrock_batch_pricing.py new file mode 100644 index 00000000000..856085ec253 --- /dev/null +++ b/tests/test_litellm/test_bedrock_batch_pricing.py @@ -0,0 +1,43 @@ +import json +from pathlib import Path + +import pytest + +PRICING_FILES = ( + "model_prices_and_context_window.json", + "litellm/model_prices_and_context_window_backup.json", +) + +BEDROCK_BATCH_MODELS = ( + "qwen.qwen3-235b-a22b-2507-v1:0", + "anthropic.claude-haiku-4-5-20251001-v1:0", + "apac.anthropic.claude-haiku-4-5-20251001-v1:0", + "au.anthropic.claude-haiku-4-5-20251001-v1:0", + "eu.anthropic.claude-haiku-4-5-20251001-v1:0", + "global.anthropic.claude-haiku-4-5-20251001-v1:0", + "jp.anthropic.claude-haiku-4-5-20251001-v1:0", + "us.anthropic.claude-haiku-4-5-20251001-v1:0", + "anthropic.claude-sonnet-4-5-20250929-v1:0", + "au.anthropic.claude-sonnet-4-5-20250929-v1:0", + "claude-sonnet-4-5-20250929-v1:0", + "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", + "global.anthropic.claude-sonnet-4-5-20250929-v1:0", + "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", +) + + +@pytest.mark.parametrize("pricing_file", PRICING_FILES) +@pytest.mark.parametrize("model", BEDROCK_BATCH_MODELS) +def test_bedrock_batch_pricing_is_half_of_on_demand( + pricing_file: str, model: str +) -> None: + model_cost_map = json.loads((Path(__file__).parents[2] / pricing_file).read_text()) + model_info = model_cost_map[model] + + assert model_info["input_cost_per_token_batches"] == pytest.approx( + model_info["input_cost_per_token"] / 2 + ) + assert model_info["output_cost_per_token_batches"] == pytest.approx( + model_info["output_cost_per_token"] / 2 + )