From 6423acc11a1577d70fa7a0aadd7ece09ca21505b Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Sun, 13 Sep 2026 04:55:39 +0000 Subject: [PATCH] chore(prices): sync prices for 5 providers: 278 models, 34 new fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4-flash-0731: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp: fireworks_ai/deepseek-v4-flash-vision-exp: fireworks_ai/accounts/fireworks/models/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/deepseek-v4p1-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p2: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/glm-5p2: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/glm-5p3-flash: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/gpt-oss-120b: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/gpt-oss-120b: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k2p6: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k2p6: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k2p7-code: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k2p7-code: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/kimi-k3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/kimi-k3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/minimax-m2p7: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/minimax-m2p7: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/minimax-m3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/minimax-m3: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/models/muse-glimmer-30b: fireworks_ai/muse-glimmer-30b: fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4: fireworks_ai/nemotron-3-ultra-nvfp4: fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b: fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b: input_cost_per_token fireworks_ai/accounts/fireworks/models/qwen3p7-plus: fireworks_ai/qwen3p7-plus: fireworks_ai/accounts/fireworks/models/qwen3p8-max: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/qwen3p8-max: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority fireworks_ai/accounts/fireworks/routers/glm-5p2-fast: fireworks_ai/accounts/fireworks/routers/glm-5p3-fast: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost fireworks_ai/accounts/fireworks/routers/kimi-k3-fast: together_ai/arcee-ai/trinity-mini: input_cost_per_token, output_cost_per_token together_ai/arize-ai/qwen-2-1.5b-instruct: babbage-002: input_cost_per_token_batches, output_cost_per_token_batches chat-latest: chatgpt-image-latest: output_cost_per_token, input_cost_per_image_token, output_cost_per_image_token, input_cost_per_token_batches, output_cost_per_token_batches claude-fable-5: claude-fable-5-1: claude-haiku-4-5: claude-mythos-5: claude-mythos-5-1: claude-opus-4-5: claude-opus-4-6: claude-opus-4-7: claude-opus-4-8: claude-opus-5: claude-sonnet-4-5: claude-sonnet-4-6: claude-sonnet-5: davinci-002: input_cost_per_token_batches, output_cost_per_token_batches deep-research-pro-preview-12-2025: cache_read_input_token_cost together_ai/deepseek-ai/deepseek-coder-33b-instruct: input_cost_per_token, output_cost_per_token together_ai/deepseek-ai/DeepSeek-R1-0528: --- ...odel_prices_and_context_window_backup.json | 968 ++++++++++++++---- model_prices_and_context_window.json | 968 ++++++++++++++---- 2 files changed, 1576 insertions(+), 360 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2220d0e1fe5..879cf894152 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -11101,12 +11101,15 @@ "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": { "input_cost_per_second": 0.001902, @@ -13171,7 +13174,9 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "deprecation_date": "2027-02-26", + "input_cost_per_second": 0.0001, + "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { "deprecation_date": "2026-10-15", @@ -13219,7 +13224,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-3-7-sonnet-20250219": { "cache_creation_input_token_cost": 3.75e-06, @@ -13378,7 +13384,8 @@ "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": { "deprecation_date": "2026-09-29", @@ -13452,7 +13459,7 @@ }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-6": { "deprecation_date": "2027-02-17", @@ -13488,7 +13495,8 @@ "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, @@ -13665,7 +13673,8 @@ "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": { "deprecation_date": "2027-02-05", @@ -13702,7 +13711,8 @@ "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": { "deprecation_date": "2027-02-05", @@ -13777,7 +13787,8 @@ }, "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": { "deprecation_date": "2027-04-16", @@ -13855,7 +13866,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { "deprecation_date": "2027-09-01", @@ -13896,7 +13907,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/fable-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5": { "deprecation_date": "2027-07-24", @@ -13937,7 +13948,7 @@ "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 512, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-8": { "deprecation_date": "2027-05-28", @@ -13977,7 +13988,8 @@ }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-20250514": { "deprecation_date": "2026-06-15", @@ -19246,12 +19258,15 @@ "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, @@ -22298,15 +22313,18 @@ "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, + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "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": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22315,14 +22333,17 @@ }, "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, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22417,14 +22438,17 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-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": 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, @@ -22433,14 +22457,17 @@ }, "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, @@ -22519,14 +22546,17 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, "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": 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, @@ -22535,14 +22565,17 @@ }, "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, "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": 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, @@ -22668,14 +22701,17 @@ }, "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 6e-07, "input_cost_per_token": 3e-07, + "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": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22684,14 +22720,17 @@ }, "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, @@ -22767,15 +22806,18 @@ "supports_vision": false }, "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-07, - "input_cost_per_token": 1.74e-06, + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "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": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22831,14 +22873,17 @@ }, "fireworks_ai/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-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": 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, @@ -22847,14 +22892,17 @@ }, "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, @@ -22893,14 +22941,17 @@ }, "fireworks_ai/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, "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": 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, @@ -22925,14 +22976,17 @@ }, "fireworks_ai/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, + "cache_read_input_token_cost_priority": 2.85e-07, "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": 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, @@ -22971,14 +23025,17 @@ }, "fireworks_ai/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 6e-07, "input_cost_per_token": 3e-07, + "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": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22987,14 +23044,17 @@ }, "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, @@ -23010,7 +23070,7 @@ "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, @@ -23287,26 +23347,28 @@ "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", @@ -23319,6 +23381,7 @@ "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 }, @@ -23375,14 +23438,15 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "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, @@ -23420,6 +23484,7 @@ "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, @@ -23439,6 +23504,7 @@ "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, @@ -23457,6 +23523,7 @@ "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, @@ -23476,6 +23543,7 @@ "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, @@ -23495,6 +23563,7 @@ "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, @@ -23505,15 +23574,18 @@ "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, + "input_cost_per_audio_token": 1e-06, + "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-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", + "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", "supported_modalities": [ "text", "image", @@ -23582,13 +23654,16 @@ "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-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-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", + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image", @@ -23651,6 +23726,8 @@ "gemini-2.5-flash": { "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", @@ -23660,7 +23737,7 @@ "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", @@ -23693,6 +23770,12 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "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_image_size": false }, "gemini-2.5-flash-image": { @@ -23700,6 +23783,9 @@ "cache_read_input_token_cost": 3e-08, "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": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -23709,8 +23795,10 @@ "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", @@ -23741,10 +23829,19 @@ "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_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, @@ -23753,8 +23850,12 @@ "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", @@ -23822,9 +23923,13 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { + "cache_read_input_token_cost": 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, @@ -23833,7 +23938,9 @@ "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", @@ -23900,9 +24007,11 @@ }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_flex": 1.25e-08, "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, @@ -23912,6 +24021,7 @@ "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", @@ -24005,7 +24115,7 @@ "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", @@ -24047,7 +24157,7 @@ "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 1.5e-08, - "cache_read_input_token_cost_priority": 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, @@ -24062,7 +24172,7 @@ "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://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", @@ -24101,6 +24211,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "deep-research-pro-preview-12-2025": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -24113,7 +24224,7 @@ "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", @@ -24137,6 +24248,8 @@ "gemini-2.5-flash-lite": { "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", @@ -24146,7 +24259,7 @@ "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", @@ -24179,6 +24292,12 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "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_image_size": false }, "gemini-2.5-flash-lite-preview-09-2025": { @@ -24330,7 +24449,7 @@ "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" ], @@ -24361,7 +24480,8 @@ "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, @@ -24461,6 +24581,9 @@ "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", @@ -24470,7 +24593,7 @@ "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" @@ -24500,7 +24623,15 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "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-pro-preview": { "deprecation_date": "2026-03-26", @@ -24575,7 +24706,7 @@ "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", @@ -24609,13 +24740,16 @@ "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", - "google_maps_grounding_cost_per_query": 0.014 + "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, @@ -25127,13 +25261,15 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_audio_token": 7e-07, "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_audio_token": 2e-05, "output_cost_per_token": 2e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -25340,7 +25476,7 @@ "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" @@ -25381,8 +25517,11 @@ }, "gemini-embedding-2": { "input_cost_per_audio_per_second": 0.00016, + "input_cost_per_audio_token": 6.5e-06, "input_cost_per_image": 0.00012, + "input_cost_per_image_token": 4.5e-07, "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, @@ -25390,7 +25529,7 @@ "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 }, @@ -27055,6 +27194,7 @@ }, "gemini-3-flash-preview": { "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", @@ -27064,7 +27204,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-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", @@ -27102,7 +27242,11 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "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, @@ -27115,7 +27259,7 @@ "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" ], @@ -27148,7 +27292,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-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", @@ -27211,7 +27355,7 @@ "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://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", @@ -27268,7 +27412,7 @@ "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://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", @@ -27325,7 +27469,7 @@ "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://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", @@ -28783,6 +28927,7 @@ "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, @@ -28791,12 +28936,15 @@ "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, @@ -28806,12 +28954,15 @@ "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, @@ -28839,7 +28990,8 @@ "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, @@ -28894,12 +29046,15 @@ "gpt-4-0613": { "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, @@ -28940,12 +29095,15 @@ "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, @@ -28989,6 +29147,7 @@ "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", @@ -29031,6 +29190,7 @@ "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", @@ -29073,6 +29233,7 @@ "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", @@ -29115,6 +29276,7 @@ "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", @@ -29153,6 +29315,7 @@ "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", @@ -29190,6 +29353,7 @@ "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", @@ -29226,6 +29390,7 @@ "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, @@ -29248,6 +29413,7 @@ "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, @@ -29270,6 +29436,7 @@ "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, @@ -29293,6 +29460,7 @@ "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, @@ -29367,6 +29535,7 @@ "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", @@ -29403,6 +29572,7 @@ "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" ], @@ -29437,6 +29607,7 @@ "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", @@ -29474,6 +29645,7 @@ "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", @@ -29511,6 +29683,7 @@ "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", @@ -29572,7 +29745,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "deprecation_date": "2027-01-20" + "deprecation_date": "2027-01-20", + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -29600,7 +29774,8 @@ "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, @@ -29621,6 +29796,7 @@ "search_context_size_low": 0.025, "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, @@ -29769,15 +29945,18 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "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" ], @@ -29909,7 +30088,9 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "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_token_cost": 1.25e-06, @@ -29919,7 +30100,10 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-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" ], @@ -29934,7 +30118,10 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-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" ], @@ -29947,7 +30134,9 @@ "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-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" @@ -30394,6 +30583,7 @@ "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", @@ -30402,6 +30592,7 @@ "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": { @@ -30409,6 +30600,7 @@ "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", @@ -30438,6 +30630,7 @@ }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, + "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, @@ -30478,11 +30671,17 @@ "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": false }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, + "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, @@ -30523,6 +30722,11 @@ "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": false }, @@ -30574,6 +30778,7 @@ }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, + "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, @@ -30615,11 +30820,17 @@ "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": false }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, + "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, @@ -30661,6 +30872,11 @@ "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": false }, @@ -30754,17 +30970,20 @@ }, "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" @@ -30793,17 +31012,20 @@ }, "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" @@ -30869,6 +31091,7 @@ "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", @@ -31005,6 +31228,7 @@ "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", @@ -31073,6 +31297,7 @@ "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", @@ -31140,6 +31365,7 @@ "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", @@ -31203,7 +31429,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", + "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "supports_parallel_function_calling": true }, @@ -31373,7 +31599,7 @@ "reasoning_effort_levels": [ "medium" ], - "source": "https://developers.openai.com/api/docs/models/chat-latest", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -31452,7 +31678,8 @@ "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 + "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, @@ -31509,7 +31736,8 @@ "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 + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-pro": { "input_cost_per_token": 3e-05, @@ -31532,6 +31760,7 @@ "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" @@ -31580,6 +31809,7 @@ "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" @@ -31657,7 +31887,8 @@ "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 + "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, @@ -31709,7 +31940,8 @@ "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 + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro": { "input_cost_per_token": 3e-05, @@ -31758,7 +31990,8 @@ "supports_xhigh_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 + "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": { "input_cost_per_token": 3e-05, @@ -31807,7 +32040,8 @@ "supports_xhigh_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 + "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, @@ -31858,6 +32092,7 @@ "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 }, @@ -31910,6 +32145,7 @@ "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 }, @@ -31959,6 +32195,7 @@ "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 }, @@ -32008,6 +32245,7 @@ "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 }, @@ -32026,6 +32264,7 @@ "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" @@ -32068,6 +32307,7 @@ "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" @@ -32100,6 +32340,7 @@ "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", @@ -32108,6 +32349,7 @@ "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": { @@ -32115,6 +32357,7 @@ "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", @@ -32439,6 +32682,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ], @@ -32469,6 +32713,7 @@ "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", @@ -32477,6 +32722,7 @@ "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": { @@ -32484,6 +32730,7 @@ "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", @@ -32517,6 +32764,7 @@ "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", @@ -32525,6 +32773,7 @@ "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": { @@ -32532,6 +32781,7 @@ "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", @@ -32563,6 +32813,7 @@ "cache_read_input_token_cost": 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", @@ -32571,12 +32822,14 @@ "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", @@ -32609,6 +32862,7 @@ "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", @@ -32617,12 +32871,14 @@ "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", @@ -32655,9 +32911,11 @@ "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, "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" @@ -32668,9 +32926,11 @@ "deprecation_date": "2026-12-01", "input_cost_per_image_token": 2.5e-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" @@ -32690,6 +32950,7 @@ "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" ], @@ -32722,6 +32983,7 @@ "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" ], @@ -32755,6 +33017,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -32790,6 +33053,7 @@ "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" ], @@ -32825,6 +33089,7 @@ "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" ], @@ -32847,8 +33112,10 @@ "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": "2027-01-20", "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": 32000, @@ -32857,6 +33124,7 @@ "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" ], @@ -32890,6 +33158,7 @@ "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" ], @@ -37609,12 +37878,15 @@ "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, @@ -37629,12 +37901,15 @@ "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, @@ -37656,6 +37931,7 @@ "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" @@ -37689,6 +37965,7 @@ "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" @@ -37716,6 +37993,7 @@ "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", @@ -37724,6 +38002,7 @@ "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, "search_context_cost_per_query": { @@ -37731,6 +38010,7 @@ "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", @@ -37760,6 +38040,7 @@ "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", @@ -37768,6 +38049,7 @@ "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, "search_context_cost_per_query": { @@ -37775,6 +38057,7 @@ "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", @@ -37884,12 +38167,15 @@ "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, @@ -37902,12 +38188,15 @@ "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, @@ -37931,6 +38220,7 @@ "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" @@ -37968,6 +38258,7 @@ "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" @@ -37991,10 +38282,11 @@ }, "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", @@ -38003,6 +38295,7 @@ "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, "search_context_cost_per_query": { @@ -38010,6 +38303,7 @@ "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, @@ -38022,10 +38316,11 @@ }, "o4-mini-2025-04-16": { "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", @@ -38034,6 +38329,7 @@ "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, "search_context_cost_per_query": { @@ -38041,6 +38337,7 @@ "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, @@ -43203,7 +43500,8 @@ "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, @@ -43214,7 +43512,8 @@ "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, @@ -43223,7 +43522,8 @@ "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, @@ -43394,7 +43694,7 @@ "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "max_input_tokens": 131072, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", @@ -43406,7 +43706,7 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -43453,7 +43753,7 @@ "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43515,7 +43815,7 @@ }, "mode": "chat", "output_cost_per_token": 1.7e-06, - "source": "https://www.together.ai/models/deepseek-v3-1", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43539,7 +43839,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43573,6 +43873,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 5.9e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43595,6 +43896,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43606,6 +43908,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.8e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43622,7 +43925,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "deprecation_date": "2026-04-02", @@ -43634,7 +43937,7 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { "deprecation_date": "2026-04-16", @@ -43642,6 +43945,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43668,7 +43972,7 @@ "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, @@ -43682,7 +43986,7 @@ "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://www.together.ai/models/gpt-oss-20b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43702,7 +44006,7 @@ "max_input_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-06, - "source": "https://www.together.ai/models/glm-4-5-air", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43718,7 +44022,7 @@ }, "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, @@ -43735,7 +44039,7 @@ }, "mode": "chat", "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/glm-4-7", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43783,7 +44087,7 @@ }, "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_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43799,7 +44103,7 @@ }, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43813,7 +44117,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, - "source": "https://www.together.ai/models/qwen3-5-397b-a17b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43828,7 +44132,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43853,7 +44157,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43868,7 +44172,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { @@ -43879,7 +44183,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 7.5e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { @@ -43889,7 +44193,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-07, @@ -43899,7 +44203,7 @@ "max_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { @@ -43909,7 +44213,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, @@ -43919,7 +44223,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43951,7 +44255,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43976,7 +44280,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -44012,7 +44316,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/moonshotai/Kimi-K2.7-Code": { @@ -44024,7 +44328,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44045,7 +44349,7 @@ "high", "max" ], - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44063,7 +44367,7 @@ "max_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44089,7 +44393,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44105,7 +44409,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/zai-org/GLM-5.2": { @@ -44117,7 +44421,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44134,7 +44438,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44151,7 +44455,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44164,6 +44468,7 @@ "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" ] @@ -44172,6 +44477,7 @@ "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" ] @@ -49497,7 +49803,8 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "deprecation_date": "2027-02-26", + "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-3": { "cache_read_input_token_cost": 2e-07, @@ -52594,10 +52901,11 @@ "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, @@ -52662,7 +52970,7 @@ "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, @@ -54561,12 +54869,13 @@ }, "gpt-4o-mini-tts-2025-03-20": { "deprecation_date": "2026-07-23", - "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" ], @@ -54579,12 +54888,13 @@ ] }, "gpt-4o-mini-tts-2025-12-15": { - "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" ], @@ -54599,24 +54909,28 @@ "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" ] @@ -54635,6 +54949,7 @@ "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, @@ -54662,6 +54977,7 @@ "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, @@ -54689,6 +55005,7 @@ "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" ], @@ -54740,13 +55057,14 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "deprecation_date": "2027-01-20" + "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://developers.openai.com/api/docs/models/gpt-realtime-whisper", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -54764,7 +55082,7 @@ "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" @@ -54778,7 +55096,7 @@ "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" @@ -54803,11 +55121,15 @@ "chatgpt-image-latest": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-01", - "input_cost_per_image_token": 1e-05, + "input_cost_per_image_token": 8e-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" @@ -57282,7 +57604,7 @@ "input_cost_per_second": 7.5e-05, "litellm_provider": "openai", "mode": "audio_transcription", - "source": "https://developers.openai.com/api/docs/models/gpt-transcribe", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime/transcription_sessions" @@ -57297,10 +57619,10 @@ "supports_audio_input": true }, "gpt-live-transcribe": { - "input_cost_per_second": 0.0002833333333333333, + "input_cost_per_second": 0.000283333333333, "litellm_provider": "openai", "mode": "audio_transcription", - "source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -57315,10 +57637,10 @@ "supports_audio_input": true }, "gpt-live-1": { - "input_cost_per_second": 0.0008333333333333334, + "input_cost_per_second": 0.000833333333333, "litellm_provider": "openai", "mode": "realtime", - "source": "https://developers.openai.com/api/docs/models/gpt-live-1", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "audio" @@ -57332,13 +57654,13 @@ "supports_function_calling": true }, "gpt-realtime-translate": { - "input_cost_per_second": 0.0005666666666666667, + "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/models/gpt-realtime-translate", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "audio" ], @@ -57366,7 +57688,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://platform.claude.com/docs/en/about-claude/models/overview", + "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, @@ -57427,7 +57749,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, @@ -57779,6 +58101,7 @@ }, "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", @@ -57881,14 +58204,17 @@ }, "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, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -57897,14 +58223,17 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57920,26 +58249,29 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": 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://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -57948,14 +58280,17 @@ }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -57964,14 +58299,17 @@ }, "fireworks_ai/deepseek-v4p1-flash": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57987,7 +58325,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -58026,19 +58364,22 @@ }, "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://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -58089,12 +58430,15 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -58110,7 +58454,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-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, @@ -58142,7 +58486,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-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, @@ -58158,7 +58502,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-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, @@ -58190,7 +58534,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-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, @@ -58199,12 +58543,15 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -58220,7 +58567,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-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, @@ -58257,7 +58604,7 @@ "high", "max" ], - "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, @@ -60955,14 +61302,17 @@ }, "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, - "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, @@ -60971,13 +61321,16 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -61005,7 +61358,7 @@ "max_output_tokens": 40960, "max_tokens": 40960, "mode": "embedding", - "source": "https://docs.fireworks.ai/serverless/pricing" + "source": "https://api.fireworks.ai/v1/serverless/models" }, "zai/glm-5.2": { "cache_creation_input_token_cost": 0, @@ -61029,7 +61382,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.6": { "deprecation_date": "2026-08-19", @@ -61039,7 +61392,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, @@ -61047,7 +61400,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/MiniMaxAI/MiniMax-M2.7": { "input_cost_per_token": 3e-07, @@ -61056,7 +61409,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 196608, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { "deprecation_date": "2026-06-22", @@ -61065,7 +61418,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 202752, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5.1": { "deprecation_date": "2026-07-10", @@ -61075,7 +61428,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 202752, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -61083,7 +61436,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 163840, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { "deprecation_date": "2026-05-14", @@ -61092,7 +61445,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { "deprecation_date": "2026-02-25", @@ -61101,7 +61454,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { "deprecation_date": "2026-04-16", @@ -61110,7 +61463,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { "input_cost_per_token": 2e-07, @@ -61118,7 +61471,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "input_cost_per_token": 6e-08, @@ -61126,7 +61479,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 131072, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-7B-Instruct-v0.3": { "input_cost_per_token": 2e-07, @@ -61134,7 +61487,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 32768, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/QwQ-32B": { "deprecation_date": "2025-11-13", @@ -61143,7 +61496,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 131072, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "cerebras/gemma-4-31b": { "input_cost_per_token": 9.9e-07, @@ -65270,5 +65623,260 @@ "supports_tool_choice": false, "supports_response_schema": 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", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models" + }, + "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" + }, + "together_ai/deepseek-ai/deepseek-coder-33b-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" + }, + "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://api.together.ai/v1/models" + }, + "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", + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "vertex_ai/gemini-2.5-flash-native-audio": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, + "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": "chat", + "output_cost_per_audio_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.1-flash-live-preview": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_second": 8.33333333333e-05, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "vertex_ai", + "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" + }, + "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": "chat", + "output_cost_per_audio_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_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-robotics-er-2": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "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" + }, + "together_ai/google/gemma-2-27b-it": { + "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" + }, + "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" + }, + "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-3-8b-chat-hf": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "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" + }, + "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" + }, + "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" + }, + "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "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" + }, + "together_ai/Qwen/Qwen2-72B-Instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2-VL-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" + }, + "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" + }, + "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" + }, + "together_ai/Qwen/Qwen2.5-Coder-32B-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" + }, + "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.together.ai/v1/models" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2220d0e1fe5..879cf894152 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -11101,12 +11101,15 @@ "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": { "input_cost_per_second": 0.001902, @@ -13171,7 +13174,9 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "deprecation_date": "2027-02-26", + "input_cost_per_second": 0.0001, + "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { "deprecation_date": "2026-10-15", @@ -13219,7 +13224,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-3-7-sonnet-20250219": { "cache_creation_input_token_cost": 3.75e-06, @@ -13378,7 +13384,8 @@ "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": { "deprecation_date": "2026-09-29", @@ -13452,7 +13459,7 @@ }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-6": { "deprecation_date": "2027-02-17", @@ -13488,7 +13495,8 @@ "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, @@ -13665,7 +13673,8 @@ "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": { "deprecation_date": "2027-02-05", @@ -13702,7 +13711,8 @@ "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": { "deprecation_date": "2027-02-05", @@ -13777,7 +13787,8 @@ }, "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": { "deprecation_date": "2027-04-16", @@ -13855,7 +13866,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { "deprecation_date": "2027-09-01", @@ -13896,7 +13907,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/fable-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5": { "deprecation_date": "2027-07-24", @@ -13937,7 +13948,7 @@ "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 512, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-8": { "deprecation_date": "2027-05-28", @@ -13977,7 +13988,8 @@ }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-20250514": { "deprecation_date": "2026-06-15", @@ -19246,12 +19258,15 @@ "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, @@ -22298,15 +22313,18 @@ "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, + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "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": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22315,14 +22333,17 @@ }, "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, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22417,14 +22438,17 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-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": 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, @@ -22433,14 +22457,17 @@ }, "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, @@ -22519,14 +22546,17 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, "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": 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, @@ -22535,14 +22565,17 @@ }, "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, "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": 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, @@ -22668,14 +22701,17 @@ }, "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 6e-07, "input_cost_per_token": 3e-07, + "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": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22684,14 +22720,17 @@ }, "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, @@ -22767,15 +22806,18 @@ "supports_vision": false }, "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-07, - "input_cost_per_token": 1.74e-06, + "cache_read_input_token_cost": 6e-07, + "cache_read_input_token_cost_priority": 6e-07, + "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": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 3.48e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22831,14 +22873,17 @@ }, "fireworks_ai/glm-5p2": { "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost_priority": 1.75e-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": 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, @@ -22847,14 +22892,17 @@ }, "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, @@ -22893,14 +22941,17 @@ }, "fireworks_ai/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-07, + "cache_read_input_token_cost_priority": 2.2e-07, "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": 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, @@ -22925,14 +22976,17 @@ }, "fireworks_ai/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-07, + "cache_read_input_token_cost_priority": 2.85e-07, "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": 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, @@ -22971,14 +23025,17 @@ }, "fireworks_ai/minimax-m2p7": { "cache_read_input_token_cost": 6e-08, + "cache_read_input_token_cost_priority": 6e-07, "input_cost_per_token": 3e-07, + "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": 1.2e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -22987,14 +23044,17 @@ }, "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, @@ -23010,7 +23070,7 @@ "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, @@ -23287,26 +23347,28 @@ "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", @@ -23319,6 +23381,7 @@ "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 }, @@ -23375,14 +23438,15 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "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, @@ -23420,6 +23484,7 @@ "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, @@ -23439,6 +23504,7 @@ "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, @@ -23457,6 +23523,7 @@ "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, @@ -23476,6 +23543,7 @@ "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, @@ -23495,6 +23563,7 @@ "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, @@ -23505,15 +23574,18 @@ "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, + "input_cost_per_audio_token": 1e-06, + "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-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", + "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", "supported_modalities": [ "text", "image", @@ -23582,13 +23654,16 @@ "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-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-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", + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image", @@ -23651,6 +23726,8 @@ "gemini-2.5-flash": { "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", @@ -23660,7 +23737,7 @@ "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", @@ -23693,6 +23770,12 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "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_image_size": false }, "gemini-2.5-flash-image": { @@ -23700,6 +23783,9 @@ "cache_read_input_token_cost": 3e-08, "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": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -23709,8 +23795,10 @@ "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", @@ -23741,10 +23829,19 @@ "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_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, @@ -23753,8 +23850,12 @@ "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", @@ -23822,9 +23923,13 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { + "cache_read_input_token_cost": 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, @@ -23833,7 +23938,9 @@ "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", @@ -23900,9 +24007,11 @@ }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_flex": 1.25e-08, "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, @@ -23912,6 +24021,7 @@ "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", @@ -24005,7 +24115,7 @@ "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", @@ -24047,7 +24157,7 @@ "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 1.5e-08, - "cache_read_input_token_cost_priority": 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, @@ -24062,7 +24172,7 @@ "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://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", @@ -24101,6 +24211,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "deep-research-pro-preview-12-2025": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -24113,7 +24224,7 @@ "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", @@ -24137,6 +24248,8 @@ "gemini-2.5-flash-lite": { "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", @@ -24146,7 +24259,7 @@ "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", @@ -24179,6 +24292,12 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "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_image_size": false }, "gemini-2.5-flash-lite-preview-09-2025": { @@ -24330,7 +24449,7 @@ "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" ], @@ -24361,7 +24480,8 @@ "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, @@ -24461,6 +24581,9 @@ "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", @@ -24470,7 +24593,7 @@ "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" @@ -24500,7 +24623,15 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "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-pro-preview": { "deprecation_date": "2026-03-26", @@ -24575,7 +24706,7 @@ "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", @@ -24609,13 +24740,16 @@ "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", - "google_maps_grounding_cost_per_query": 0.014 + "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, @@ -25127,13 +25261,15 @@ "cache_read_input_token_cost": 1.25e-07, "input_cost_per_audio_token": 7e-07, "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_audio_token": 2e-05, "output_cost_per_token": 2e-05, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -25340,7 +25476,7 @@ "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" @@ -25381,8 +25517,11 @@ }, "gemini-embedding-2": { "input_cost_per_audio_per_second": 0.00016, + "input_cost_per_audio_token": 6.5e-06, "input_cost_per_image": 0.00012, + "input_cost_per_image_token": 4.5e-07, "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, "input_cost_per_video_per_second": 0.00079, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, @@ -25390,7 +25529,7 @@ "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 }, @@ -27055,6 +27194,7 @@ }, "gemini-3-flash-preview": { "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", @@ -27064,7 +27204,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-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", @@ -27102,7 +27242,11 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "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, @@ -27115,7 +27259,7 @@ "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" ], @@ -27148,7 +27292,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-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", @@ -27211,7 +27355,7 @@ "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://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", @@ -27268,7 +27412,7 @@ "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://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", @@ -27325,7 +27469,7 @@ "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://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", @@ -28783,6 +28927,7 @@ "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, @@ -28791,12 +28936,15 @@ "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, @@ -28806,12 +28954,15 @@ "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, @@ -28839,7 +28990,8 @@ "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, @@ -28894,12 +29046,15 @@ "gpt-4-0613": { "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, @@ -28940,12 +29095,15 @@ "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, @@ -28989,6 +29147,7 @@ "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", @@ -29031,6 +29190,7 @@ "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", @@ -29073,6 +29233,7 @@ "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", @@ -29115,6 +29276,7 @@ "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", @@ -29153,6 +29315,7 @@ "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", @@ -29190,6 +29353,7 @@ "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", @@ -29226,6 +29390,7 @@ "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, @@ -29248,6 +29413,7 @@ "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, @@ -29270,6 +29436,7 @@ "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, @@ -29293,6 +29460,7 @@ "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, @@ -29367,6 +29535,7 @@ "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", @@ -29403,6 +29572,7 @@ "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" ], @@ -29437,6 +29607,7 @@ "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", @@ -29474,6 +29645,7 @@ "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", @@ -29511,6 +29683,7 @@ "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", @@ -29572,7 +29745,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "deprecation_date": "2027-01-20" + "deprecation_date": "2027-01-20", + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -29600,7 +29774,8 @@ "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, @@ -29621,6 +29796,7 @@ "search_context_size_low": 0.025, "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, @@ -29769,15 +29945,18 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "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" ], @@ -29909,7 +30088,9 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "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_token_cost": 1.25e-06, @@ -29919,7 +30100,10 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-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" ], @@ -29934,7 +30118,10 @@ "mode": "image_generation", "output_cost_per_token": 1e-05, "input_cost_per_image_token": 8e-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" ], @@ -29947,7 +30134,9 @@ "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-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" @@ -30394,6 +30583,7 @@ "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", @@ -30402,6 +30592,7 @@ "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": { @@ -30409,6 +30600,7 @@ "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", @@ -30438,6 +30630,7 @@ }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, + "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, @@ -30478,11 +30671,17 @@ "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": false }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, + "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, @@ -30523,6 +30722,11 @@ "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": false }, @@ -30574,6 +30778,7 @@ }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, + "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, @@ -30615,11 +30820,17 @@ "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": false }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, + "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, @@ -30661,6 +30872,11 @@ "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": false }, @@ -30754,17 +30970,20 @@ }, "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" @@ -30793,17 +31012,20 @@ }, "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" @@ -30869,6 +31091,7 @@ "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", @@ -31005,6 +31228,7 @@ "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", @@ -31073,6 +31297,7 @@ "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", @@ -31140,6 +31365,7 @@ "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", @@ -31203,7 +31429,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", + "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "supports_parallel_function_calling": true }, @@ -31373,7 +31599,7 @@ "reasoning_effort_levels": [ "medium" ], - "source": "https://developers.openai.com/api/docs/models/chat-latest", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -31452,7 +31678,8 @@ "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 + "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, @@ -31509,7 +31736,8 @@ "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 + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-pro": { "input_cost_per_token": 3e-05, @@ -31532,6 +31760,7 @@ "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" @@ -31580,6 +31809,7 @@ "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" @@ -31657,7 +31887,8 @@ "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 + "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, @@ -31709,7 +31940,8 @@ "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 + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.4-pro": { "input_cost_per_token": 3e-05, @@ -31758,7 +31990,8 @@ "supports_xhigh_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 + "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": { "input_cost_per_token": 3e-05, @@ -31807,7 +32040,8 @@ "supports_xhigh_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 + "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, @@ -31858,6 +32092,7 @@ "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 }, @@ -31910,6 +32145,7 @@ "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 }, @@ -31959,6 +32195,7 @@ "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 }, @@ -32008,6 +32245,7 @@ "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 }, @@ -32026,6 +32264,7 @@ "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" @@ -32068,6 +32307,7 @@ "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" @@ -32100,6 +32340,7 @@ "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", @@ -32108,6 +32349,7 @@ "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": { @@ -32115,6 +32357,7 @@ "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", @@ -32439,6 +32682,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses" ], @@ -32469,6 +32713,7 @@ "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", @@ -32477,6 +32722,7 @@ "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": { @@ -32484,6 +32730,7 @@ "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", @@ -32517,6 +32764,7 @@ "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", @@ -32525,6 +32773,7 @@ "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": { @@ -32532,6 +32781,7 @@ "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", @@ -32563,6 +32813,7 @@ "cache_read_input_token_cost": 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", @@ -32571,12 +32822,14 @@ "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", @@ -32609,6 +32862,7 @@ "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", @@ -32617,12 +32871,14 @@ "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", @@ -32655,9 +32911,11 @@ "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, "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" @@ -32668,9 +32926,11 @@ "deprecation_date": "2026-12-01", "input_cost_per_image_token": 2.5e-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" @@ -32690,6 +32950,7 @@ "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" ], @@ -32722,6 +32983,7 @@ "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" ], @@ -32755,6 +33017,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], @@ -32790,6 +33053,7 @@ "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" ], @@ -32825,6 +33089,7 @@ "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" ], @@ -32847,8 +33112,10 @@ "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": "2027-01-20", "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": 32000, @@ -32857,6 +33124,7 @@ "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" ], @@ -32890,6 +33158,7 @@ "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" ], @@ -37609,12 +37878,15 @@ "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, @@ -37629,12 +37901,15 @@ "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, @@ -37656,6 +37931,7 @@ "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" @@ -37689,6 +37965,7 @@ "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" @@ -37716,6 +37993,7 @@ "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", @@ -37724,6 +38002,7 @@ "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, "search_context_cost_per_query": { @@ -37731,6 +38010,7 @@ "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", @@ -37760,6 +38040,7 @@ "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", @@ -37768,6 +38049,7 @@ "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, "search_context_cost_per_query": { @@ -37775,6 +38057,7 @@ "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", @@ -37884,12 +38167,15 @@ "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, @@ -37902,12 +38188,15 @@ "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, @@ -37931,6 +38220,7 @@ "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" @@ -37968,6 +38258,7 @@ "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" @@ -37991,10 +38282,11 @@ }, "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", @@ -38003,6 +38295,7 @@ "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, "search_context_cost_per_query": { @@ -38010,6 +38303,7 @@ "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, @@ -38022,10 +38316,11 @@ }, "o4-mini-2025-04-16": { "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", @@ -38034,6 +38329,7 @@ "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, "search_context_cost_per_query": { @@ -38041,6 +38337,7 @@ "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, @@ -43203,7 +43500,8 @@ "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, @@ -43214,7 +43512,8 @@ "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, @@ -43223,7 +43522,8 @@ "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, @@ -43394,7 +43694,7 @@ "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "max_input_tokens": 131072, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", @@ -43406,7 +43706,7 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "deprecation_date": "2026-07-10", @@ -43453,7 +43753,7 @@ "max_input_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43515,7 +43815,7 @@ }, "mode": "chat", "output_cost_per_token": 1.7e-06, - "source": "https://www.together.ai/models/deepseek-v3-1", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43539,7 +43839,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43573,6 +43873,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 5.9e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43595,6 +43896,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43606,6 +43908,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.8e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43622,7 +43925,7 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { "deprecation_date": "2026-04-02", @@ -43634,7 +43937,7 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "max_input_tokens": 32768, - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { "deprecation_date": "2026-04-16", @@ -43642,6 +43945,7 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43668,7 +43972,7 @@ "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, @@ -43682,7 +43986,7 @@ "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://www.together.ai/models/gpt-oss-20b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43702,7 +44006,7 @@ "max_input_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-06, - "source": "https://www.together.ai/models/glm-4-5-air", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43718,7 +44022,7 @@ }, "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, @@ -43735,7 +44039,7 @@ }, "mode": "chat", "output_cost_per_token": 2e-06, - "source": "https://www.together.ai/models/glm-4-7", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43783,7 +44087,7 @@ }, "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_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43799,7 +44103,7 @@ }, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -43813,7 +44117,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, - "source": "https://www.together.ai/models/qwen3-5-397b-a17b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43828,7 +44132,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43853,7 +44157,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -43868,7 +44172,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { @@ -43879,7 +44183,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 7.5e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { @@ -43889,7 +44193,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-07, @@ -43899,7 +44203,7 @@ "max_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { @@ -43909,7 +44213,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, @@ -43919,7 +44223,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43951,7 +44255,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -43976,7 +44280,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -44012,7 +44316,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/moonshotai/Kimi-K2.7-Code": { @@ -44024,7 +44328,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44045,7 +44349,7 @@ "high", "max" ], - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44063,7 +44367,7 @@ "max_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44089,7 +44393,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44105,7 +44409,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/zai-org/GLM-5.2": { @@ -44117,7 +44421,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44134,7 +44438,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44151,7 +44455,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -44164,6 +44468,7 @@ "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" ] @@ -44172,6 +44477,7 @@ "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" ] @@ -49497,7 +49803,8 @@ "supported_endpoints": [ "/v1/audio/transcriptions" ], - "deprecation_date": "2027-02-26" + "deprecation_date": "2027-02-26", + "source": "https://developers.openai.com/api/docs/pricing" }, "xai/grok-3": { "cache_read_input_token_cost": 2e-07, @@ -52594,10 +52901,11 @@ "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, @@ -52662,7 +52970,7 @@ "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, @@ -54561,12 +54869,13 @@ }, "gpt-4o-mini-tts-2025-03-20": { "deprecation_date": "2026-07-23", - "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" ], @@ -54579,12 +54888,13 @@ ] }, "gpt-4o-mini-tts-2025-12-15": { - "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" ], @@ -54599,24 +54909,28 @@ "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" ] @@ -54635,6 +54949,7 @@ "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, @@ -54662,6 +54977,7 @@ "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, @@ -54689,6 +55005,7 @@ "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" ], @@ -54740,13 +55057,14 @@ "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "deprecation_date": "2027-01-20" + "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://developers.openai.com/api/docs/models/gpt-realtime-whisper", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -54764,7 +55082,7 @@ "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" @@ -54778,7 +55096,7 @@ "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" @@ -54803,11 +55121,15 @@ "chatgpt-image-latest": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-01", - "input_cost_per_image_token": 1e-05, + "input_cost_per_image_token": 8e-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" @@ -57282,7 +57604,7 @@ "input_cost_per_second": 7.5e-05, "litellm_provider": "openai", "mode": "audio_transcription", - "source": "https://developers.openai.com/api/docs/models/gpt-transcribe", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/audio/transcriptions", "/v1/realtime/transcription_sessions" @@ -57297,10 +57619,10 @@ "supports_audio_input": true }, "gpt-live-transcribe": { - "input_cost_per_second": 0.0002833333333333333, + "input_cost_per_second": 0.000283333333333, "litellm_provider": "openai", "mode": "audio_transcription", - "source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" @@ -57315,10 +57637,10 @@ "supports_audio_input": true }, "gpt-live-1": { - "input_cost_per_second": 0.0008333333333333334, + "input_cost_per_second": 0.000833333333333, "litellm_provider": "openai", "mode": "realtime", - "source": "https://developers.openai.com/api/docs/models/gpt-live-1", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "text", "audio" @@ -57332,13 +57654,13 @@ "supports_function_calling": true }, "gpt-realtime-translate": { - "input_cost_per_second": 0.0005666666666666667, + "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/models/gpt-realtime-translate", + "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ "audio" ], @@ -57366,7 +57688,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://platform.claude.com/docs/en/about-claude/models/overview", + "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, @@ -57427,7 +57749,7 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, @@ -57779,6 +58101,7 @@ }, "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", @@ -57881,14 +58204,17 @@ }, "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, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -57897,14 +58223,17 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57920,26 +58249,29 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": 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://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -57948,14 +58280,17 @@ }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -57964,14 +58299,17 @@ }, "fireworks_ai/deepseek-v4p1-flash": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "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": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", + "output_cost_per_token_priority": 8.25e-07, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -57987,7 +58325,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -58026,19 +58364,22 @@ }, "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://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -58089,12 +58430,15 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -58110,7 +58454,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-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, @@ -58142,7 +58486,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-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, @@ -58158,7 +58502,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-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, @@ -58190,7 +58534,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-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, @@ -58199,12 +58543,15 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -58220,7 +58567,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-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, @@ -58257,7 +58604,7 @@ "high", "max" ], - "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, @@ -60955,14 +61302,17 @@ }, "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, - "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, @@ -60971,13 +61321,16 @@ }, "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, - "source": "https://docs.fireworks.ai/serverless/pricing", + "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, @@ -61005,7 +61358,7 @@ "max_output_tokens": 40960, "max_tokens": 40960, "mode": "embedding", - "source": "https://docs.fireworks.ai/serverless/pricing" + "source": "https://api.fireworks.ai/v1/serverless/models" }, "zai/glm-5.2": { "cache_creation_input_token_cost": 0, @@ -61029,7 +61382,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.6": { "deprecation_date": "2026-08-19", @@ -61039,7 +61392,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-07, @@ -61047,7 +61400,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/MiniMaxAI/MiniMax-M2.7": { "input_cost_per_token": 3e-07, @@ -61056,7 +61409,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 196608, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { "deprecation_date": "2026-06-22", @@ -61065,7 +61418,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 202752, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5.1": { "deprecation_date": "2026-07-10", @@ -61075,7 +61428,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 202752, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -61083,7 +61436,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 163840, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { "deprecation_date": "2026-05-14", @@ -61092,7 +61445,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { "deprecation_date": "2026-02-25", @@ -61101,7 +61454,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { "deprecation_date": "2026-04-16", @@ -61110,7 +61463,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { "input_cost_per_token": 2e-07, @@ -61118,7 +61471,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 262144, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "input_cost_per_token": 6e-08, @@ -61126,7 +61479,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 131072, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-7B-Instruct-v0.3": { "input_cost_per_token": 2e-07, @@ -61134,7 +61487,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 32768, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/QwQ-32B": { "deprecation_date": "2025-11-13", @@ -61143,7 +61496,7 @@ "litellm_provider": "together_ai", "max_input_tokens": 131072, "mode": "chat", - "source": "https://api.together.xyz/v1/models" + "source": "https://api.together.ai/v1/models" }, "cerebras/gemma-4-31b": { "input_cost_per_token": 9.9e-07, @@ -65270,5 +65623,260 @@ "supports_tool_choice": false, "supports_response_schema": 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", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://api.fireworks.ai/v1/serverless/models" + }, + "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" + }, + "together_ai/deepseek-ai/deepseek-coder-33b-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" + }, + "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://api.together.ai/v1/models" + }, + "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", + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models" + }, + "vertex_ai/gemini-2.5-flash-native-audio": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 5e-07, + "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": "chat", + "output_cost_per_audio_token": 1e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-3.1-flash-live-preview": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_second": 8.33333333333e-05, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "vertex_ai", + "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" + }, + "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": "chat", + "output_cost_per_audio_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_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-robotics-er-2": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "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" + }, + "together_ai/google/gemma-2-27b-it": { + "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" + }, + "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" + }, + "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-3-8b-chat-hf": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "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" + }, + "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" + }, + "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" + }, + "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "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": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://api.together.ai/v1/models" + }, + "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" + }, + "together_ai/Qwen/Qwen2-72B-Instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/Qwen/Qwen2-VL-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" + }, + "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" + }, + "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" + }, + "together_ai/Qwen/Qwen2.5-Coder-32B-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" + }, + "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://api.together.ai/v1/models" } }