From b7017a79497012fc5e1bfb533d414c600e121aa0 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 20 Aug 2026 18:13:39 +0000 Subject: [PATCH] fix(model_prices): consolidate nine open registry audits into one changeset Combines the model-cost-map data from #35911, #36017, #36080, #36113, #36188, #36444, #37029, #37252 and #37632 onto current litellm_internal_staging, merged per entry field so older branches no longer revert fields the base has gained since they were opened. Drops the Gemini deprecation dates from #36188 and the text-embedding-004 date from #36080 that the official docs contradict. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 438 ++++++++++++++++-- model_prices_and_context_window.json | 438 ++++++++++++++++-- .../llm_cost_calc/test_llm_cost_calc_utils.py | 41 ++ ...est_gemini_3_1_flash_lite_image_pricing.py | 150 ++++++ 4 files changed, 979 insertions(+), 88 deletions(-) create mode 100644 tests/test_litellm/test_gemini_3_1_flash_lite_image_pricing.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index db6627bad58..5ef50ed4dc5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12401,8 +12401,8 @@ "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -12787,7 +12787,8 @@ "us": 1.1 }, "supports_output_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true }, "claude-opus-5": { "deprecation_date": "2027-07-24", @@ -13350,7 +13351,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2e-06, + "deprecation_date": "2025-09-15" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, @@ -13371,7 +13373,8 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-nightly": { "input_cost_per_token": 1e-06, @@ -13391,7 +13394,8 @@ "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, @@ -13413,7 +13417,8 @@ "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, @@ -18893,6 +18898,106 @@ }, "web_search_billing_unit": "per_query" }, + "gemini-3.1-flash-lite-image": { + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "gemini/gemini-3.1-flash-lite-image": { + "rpm": 1000, + "tpm": 4000000, + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "vertex_ai/gemini-3.1-flash-lite-image": { + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, "gemini-3.1-flash-image": { "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -24142,7 +24247,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2027-01-20" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -25567,6 +25673,154 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-5.6-cyber": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/gpt-5.6-cyber", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-blue-latest": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "chat-latest": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://platform.openai.com/docs/models/chat-latest", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, @@ -29330,28 +29584,30 @@ "mistral/codestral-2508": { "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://mistral.ai/news/codestral-25-08", + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-latest": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 9e-07, "supports_assistant_prefill": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_function_calling": true }, "mistral/codestral-mamba-latest": { "input_cost_per_token": 2.5e-07, @@ -29550,6 +29806,16 @@ ], "source": "https://mistral.ai/pricing#api-pricing" }, + "mistral/mistral-ocr-4-1": { + "annotation_cost_per_page": 0.005, + "litellm_provider": "mistral", + "mode": "ocr", + "ocr_cost_per_page": 0.004, + "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", + "supported_endpoints": [ + "/v1/ocr" + ] + }, "mistral/mistral-ocr-2505-completion": { "deprecation_date": "2026-05-31", "litellm_provider": "mistral", @@ -29874,19 +30140,19 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", + "output_cost_per_token": 6e-07, + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true }, "mistral/mistral-small-3-2-2506": { "deprecation_date": "2026-07-31", @@ -32708,6 +32974,31 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5": { + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://openrouter.ai/anthropic/claude-opus-5", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "openrouter/bytedance/ui-tars-1.5-7b": { "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -32816,6 +33107,38 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/deepseek/deepseek-v4-pro": { + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-v4-pro-0813": { + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "openrouter/google/gemini-2.0-flash-001": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, @@ -35341,7 +35664,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "deprecation_date": "2025-04-30" }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, @@ -35361,7 +35685,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "deprecation_date": "2025-04-30" }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, @@ -39813,13 +40138,13 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 1.35e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5.4e-06, + "output_cost_per_token": 1.7e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" @@ -40653,13 +40978,13 @@ "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 9e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-07, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, @@ -40741,13 +41066,13 @@ "supports_web_search": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-06, + "output_cost_per_token": 8.8e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", @@ -40757,13 +41082,13 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-06, + "output_cost_per_token": 1.8e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" @@ -41738,7 +42063,8 @@ "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-3-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -41856,7 +42182,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-fast-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -41925,7 +42252,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-1-fast": { "cache_read_input_token_cost": 5e-08, @@ -42253,7 +42581,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, @@ -42273,7 +42602,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-code-fast-1-0825": { "cache_read_input_token_cost": 2e-07, @@ -42293,7 +42623,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-vision-beta": { "input_cost_per_image": 5e-06, @@ -46643,7 +46974,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2027-01-20" }, "gpt-realtime-whisper": { "input_cost_per_second": 0.0002833333333333333, @@ -48700,7 +49032,8 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, @@ -48733,7 +49066,8 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true }, "gemini/gemini-robotics-er-2-streaming-preview": { "input_cost_per_audio_token": 2e-06, @@ -48850,6 +49184,22 @@ ], "supports_audio_output": true }, + "mistral/zai-glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/model-cards/zai-glm-5-2", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fallback_generalizations": { "rules": [ { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index db6627bad58..5ef50ed4dc5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12401,8 +12401,8 @@ "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -12787,7 +12787,8 @@ "us": 1.1 }, "supports_output_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true }, "claude-opus-5": { "deprecation_date": "2027-07-24", @@ -13350,7 +13351,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2e-06, + "deprecation_date": "2025-09-15" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, @@ -13371,7 +13373,8 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-nightly": { "input_cost_per_token": 1e-06, @@ -13391,7 +13394,8 @@ "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-r-08-2024": { "input_cost_per_token": 1.5e-07, @@ -13413,7 +13417,8 @@ "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2025-09-15" }, "command-r-plus-08-2024": { "input_cost_per_token": 2.5e-06, @@ -18893,6 +18898,106 @@ }, "web_search_billing_unit": "per_query" }, + "gemini-3.1-flash-lite-image": { + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "gemini/gemini-3.1-flash-lite-image": { + "rpm": 1000, + "tpm": 4000000, + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "litellm_provider": "gemini", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, + "vertex_ai/gemini-3.1-flash-lite-image": { + "input_cost_per_image": 0.00028, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_vision": true + }, "gemini-3.1-flash-image": { "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, @@ -24142,7 +24247,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2027-01-20" }, "gpt-4o-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -25567,6 +25673,154 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "gpt-5.6-cyber": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/gpt-5.6-cyber", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-red-latest": { + "cache_creation_input_token_cost": 1.5625e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3.125e-05, + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-06, + "input_cost_per_token": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_above_272k_tokens": 0.0001125, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/daybreak-red-latest", + "supports_computer_use": true, + "supports_parallel_function_calling": true + }, + "daybreak-blue-latest": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://platform.openai.com/docs/models/daybreak-blue-latest", + "supports_parallel_function_calling": true + }, + "chat-latest": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://platform.openai.com/docs/models/chat-latest", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, @@ -29330,28 +29584,30 @@ "mistral/codestral-2508": { "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://mistral.ai/news/codestral-25-08", + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, "mistral/codestral-latest": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 3e-07, "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 9e-07, "supports_assistant_prefill": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", + "supports_function_calling": true }, "mistral/codestral-mamba-latest": { "input_cost_per_token": 2.5e-07, @@ -29550,6 +29806,16 @@ ], "source": "https://mistral.ai/pricing#api-pricing" }, + "mistral/mistral-ocr-4-1": { + "annotation_cost_per_page": 0.005, + "litellm_provider": "mistral", + "mode": "ocr", + "ocr_cost_per_page": 0.004, + "source": "https://docs.mistral.ai/models/model-cards/ocr-4-1", + "supported_endpoints": [ + "/v1/ocr" + ] + }, "mistral/mistral-ocr-2505-completion": { "deprecation_date": "2026-05-31", "litellm_provider": "mistral", @@ -29874,19 +30140,19 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://mistral.ai/pricing", + "output_cost_per_token": 6e-07, + "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true }, "mistral/mistral-small-3-2-2506": { "deprecation_date": "2026-07-31", @@ -32708,6 +32974,31 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5": { + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://openrouter.ai/anthropic/claude-opus-5", + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "openrouter/bytedance/ui-tars-1.5-7b": { "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -32816,6 +33107,38 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/deepseek/deepseek-v4-pro": { + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-v4-pro-0813": { + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "openrouter/google/gemini-2.0-flash-001": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, @@ -35341,7 +35664,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "deprecation_date": "2025-04-30" }, "rerank-english-v3.0": { "input_cost_per_query": 0.002, @@ -35361,7 +35685,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "deprecation_date": "2025-04-30" }, "rerank-multilingual-v3.0": { "input_cost_per_query": 0.002, @@ -39813,13 +40138,13 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { - "input_cost_per_token": 1.35e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5.4e-06, + "output_cost_per_token": 1.7e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" @@ -40653,13 +40978,13 @@ "supports_vision": true }, "vertex_ai/openai/gpt-oss-120b-maas": { - "input_cost_per_token": 1.5e-07, + "input_cost_per_token": 9e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-07, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true }, @@ -40741,13 +41066,13 @@ "supports_web_search": true }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "input_cost_per_token": 2.5e-07, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1e-06, + "output_cost_per_token": 8.8e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", @@ -40757,13 +41082,13 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 2.2e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-06, + "output_cost_per_token": 1.8e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" @@ -41738,7 +42063,8 @@ "supports_prompt_caching": true, "supports_response_schema": false, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-3-mini": { "cache_read_input_token_cost": 7.5e-08, @@ -41856,7 +42182,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-fast-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -41925,7 +42252,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_web_search": true, + "deprecation_date": "2026-05-15" }, "xai/grok-4-1-fast": { "cache_read_input_token_cost": 5e-08, @@ -42253,7 +42581,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-07, @@ -42273,7 +42602,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-code-fast-1-0825": { "cache_read_input_token_cost": 2e-07, @@ -42293,7 +42623,8 @@ "output_cost_per_token_above_200k_tokens": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "deprecation_date": "2026-05-15" }, "xai/grok-vision-beta": { "input_cost_per_image": 5e-06, @@ -46643,7 +46974,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2027-01-20" }, "gpt-realtime-whisper": { "input_cost_per_second": 0.0002833333333333333, @@ -48700,7 +49032,8 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true }, "claude-mythos-preview": { "cache_creation_input_token_cost": 1.25e-05, @@ -48733,7 +49066,8 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true }, "gemini/gemini-robotics-er-2-streaming-preview": { "input_cost_per_audio_token": 2e-06, @@ -48850,6 +49184,22 @@ ], "supports_audio_output": true }, + "mistral/zai-glm-5-2": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/model-cards/zai-glm-5-2", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fallback_generalizations": { "rules": [ { diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 06be96fefdf..1cecd3e5f7c 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -1056,6 +1056,47 @@ def test_generic_cost_per_token_gpt56_terra_cache_costs_by_tier_and_context( assert prompt_cost == pytest.approx(expected_prompt_cost) +@pytest.mark.parametrize("model", ["gpt-5.6-cyber", "daybreak-red-latest"]) +@pytest.mark.parametrize( + "prompt_tokens,input_rate,cache_write_rate,cache_read_rate,output_rate", + [ + (100000, 1.25e-5, 1.5625e-5, 1.25e-6, 7.5e-5), + (300000, 2.5e-5, 3.125e-5, 2.5e-6, 1.125e-4), + ], +) +def test_generic_cost_per_token_gpt56_cyber( + model, prompt_tokens, input_rate, cache_write_rate, cache_read_rate, output_rate +): + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + cached_tokens = 50000 + cache_write_tokens = 40000 + text_tokens = prompt_tokens - cached_tokens - cache_write_tokens + completion_tokens = 1000 + usage = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + prompt_tokens_details=PromptTokensDetailsWrapper( + cached_tokens=cached_tokens, cache_write_tokens=cache_write_tokens + ), + ) + + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider="openai", + ) + + assert prompt_cost == pytest.approx( + text_tokens * input_rate + + cached_tokens * cache_read_rate + + cache_write_tokens * cache_write_rate + ) + assert completion_cost == pytest.approx(completion_tokens * output_rate) + + @pytest.mark.parametrize( "model,input_cost,output_cost,cache_read_cost", [ diff --git a/tests/test_litellm/test_gemini_3_1_flash_lite_image_pricing.py b/tests/test_litellm/test_gemini_3_1_flash_lite_image_pricing.py new file mode 100644 index 00000000000..adc306971e3 --- /dev/null +++ b/tests/test_litellm/test_gemini_3_1_flash_lite_image_pricing.py @@ -0,0 +1,150 @@ +"""Pricing entry for ``gemini-3.1-flash-lite-image`` (Google's Nano Banana 2 Lite). + +Google publishes: $0.25/1M input, $1.50/1M text output, and $30/1M image-output +tokens for the Lite image model (https://cloud.google.com/vertex-ai/generative-ai/pricing). +A 1K image is ~1120 output image tokens => ~$0.0336 / image. + +Without this entry, ``completion_cost`` raises "model isn't mapped yet" and Vertex +generateContent pass-through cost tracking silently logs $0. These tests pin the +values in both the primary price map and the ``litellm/`` backup, and verify +``get_model_info`` / ``completion_cost`` surface them. +""" + +import json +import os +import sys + +sys.path.insert(0, os.path.abspath("../..")) + +import litellm +from litellm import completion_cost +from litellm.types.utils import CompletionTokensDetailsWrapper, ModelResponse, Usage + +VARIANTS = [ + "gemini-3.1-flash-lite-image", + "gemini/gemini-3.1-flash-lite-image", + "vertex_ai/gemini-3.1-flash-lite-image", +] + +EXPECTED = { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "output_cost_per_image_token": 3e-05, + "mode": "image_generation", +} + +EXPECTED_CAPABILITIES = { + "max_output_tokens": 4096, + "max_tokens": 4096, + "supports_response_schema": False, + "supports_reasoning": True, +} + +EXPECTED_PER_ROUTE = { + "gemini-3.1-flash-lite-image": { + "supports_prompt_caching": True, + "supports_function_calling": False, + }, + "vertex_ai/gemini-3.1-flash-lite-image": { + "supports_prompt_caching": True, + "supports_function_calling": False, + }, + "gemini/gemini-3.1-flash-lite-image": { + "supports_prompt_caching": False, + "supports_function_calling": True, + "input_cost_per_token_batches": 1.25e-07, + "output_cost_per_token_batches": 7.5e-07, + }, +} + + +def _load_json(path: str) -> dict: + with open(path, encoding="utf-8") as f: + return json.load(f) + + +def _backup_path() -> str: + return os.path.join( + os.path.dirname(litellm.__file__), + "model_prices_and_context_window_backup.json", + ) + + +def _main_path() -> str: + return os.path.join( + os.path.dirname(__file__), "..", "..", "model_prices_and_context_window.json" + ) + + +class TestGeminiFlashLiteImagePricingData: + """Both price maps must carry Google's published Nano Banana 2 Lite costs.""" + + def test_present_in_both_maps(self): + main = _load_json(_main_path()) + backup = _load_json(_backup_path()) + for key in VARIANTS: + for label, data in (("main", main), ("backup", backup)): + assert key in data, f"{key} missing from {label} JSON" + entry = data[key] + for field, value in EXPECTED.items(): + assert entry[field] == value, f"{key} {field} in {label}: {entry.get(field)} != {value}" + + def test_capabilities_match_model_cards(self): + main = _load_json(_main_path()) + backup = _load_json(_backup_path()) + for key in VARIANTS: + expected = {**EXPECTED_CAPABILITIES, **EXPECTED_PER_ROUTE[key]} + for label, data in (("main", main), ("backup", backup)): + entry = data[key] + for field, value in expected.items(): + assert entry[field] == value, f"{key} {field} in {label}: {entry.get(field)} != {value}" + + def test_grounding_fields_absent(self): + """Grounding with Google Search is unsupported on Lite, so no search pricing.""" + for path in (_main_path(), _backup_path()): + data = _load_json(path) + for key in VARIANTS: + for field in ( + "supports_web_search", + "search_context_cost_per_query", + "web_search_billing_unit", + ): + assert field not in data[key], f"{key} should not define {field}" + + def test_image_output_pricing_consistent(self): + """1120 image-output tokens * output_cost_per_image_token == output_cost_per_image.""" + backup = _load_json(_backup_path()) + entry = backup["gemini-3.1-flash-lite-image"] + assert round(1120 * entry["output_cost_per_image_token"], 6) == entry["output_cost_per_image"] + + +class TestGeminiFlashLiteImageModelInfo: + """``get_model_info`` and ``completion_cost`` must report the new costs.""" + + def test_get_model_info_and_cost(self): + original = litellm.model_cost + try: + litellm.model_cost = _load_json(_backup_path()) + info = litellm.get_model_info("gemini-3.1-flash-lite-image") + assert info["input_cost_per_token"] == EXPECTED["input_cost_per_token"] + assert info["output_cost_per_token"] == EXPECTED["output_cost_per_token"] + + resp = ModelResponse() + resp.model = "gemini-3.1-flash-lite-image" + resp.usage = Usage( + prompt_tokens=7, + completion_tokens=1120, + total_tokens=1127, + completion_tokens_details=CompletionTokensDetailsWrapper( + image_tokens=1120, text_tokens=0 + ), + ) + cost = completion_cost( + completion_response=resp, + model="gemini-3.1-flash-lite-image", + custom_llm_provider="vertex_ai", + ) + expected_cost = 1120 * 3e-05 + 7 * 2.5e-07 + assert abs(cost - expected_cost) < 1e-6, f"unexpected cost {cost}" + finally: + litellm.model_cost = original