From 177916cd165e88b018cab125db4be42a5852721d Mon Sep 17 00:00:00 2001 From: Dushyant Acharya Date: Fri, 12 Jun 2026 19:39:51 +0530 Subject: [PATCH] fix(tests): correct deepseek model cache prices and update JSON schema - Appended both prefixed and bare deepseek-v4 models to satisfy test assertions - Corrected deepseek-v4-pro expected cache hit and token prices based on latest review updates - Added missing realtime endpoint to test_utils.py INTENDED_SCHEMA --- ...odel_prices_and_context_window_backup.json | 240 +++++++++++++----- model_prices_and_context_window.json | 62 ++++- tests/test_litellm/test_utils.py | 1 + 3 files changed, 232 insertions(+), 71 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 191d0d341c5..3945227327d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4409,6 +4409,23 @@ "/v1/audio/transcriptions" ] }, + "azure/gpt-realtime-whisper": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "azure", + "mode": "audio_transcription", + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "azure/gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_priority": 2.5e-07, @@ -7557,6 +7574,45 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "azure_ai/deepseek-v3.1": { + "input_cost_per_token": 1.23e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.94e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v4-pro": { + "input_cost_per_token": 1.74e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.48e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v4-flash": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 5.1e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/embed-v-4-0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", @@ -10854,38 +10910,6 @@ "supports_system_messages": true, "supports_tool_choice": false }, - "deepseek-v4-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "deepseek", - "max_input_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "deepseek-v4-pro": { - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "deepseek", - "max_input_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "dashscope/qwen-coder": { "input_cost_per_token": 3e-07, "litellm_provider": "dashscope", @@ -13478,38 +13502,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "deepseek/deepseek-v4-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "deepseek", - "max_input_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "deepseek/deepseek-v4-pro": { - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "deepseek", - "max_input_tokens": 1000000, - "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://api-docs.deepseek.com/quick_start/pricing", - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "deepseek.v3-v1:0": { "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", @@ -40980,6 +40972,23 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-realtime-whisper": { + "input_cost_per_second": 0.0002833333333333333, + "litellm_provider": "openai", + "mode": "audio_transcription", + "source": "https://platform.openai.com/docs/models/gpt-realtime-whisper", + "supported_endpoints": [ + "/v1/realtime", + "/v1/realtime/transcription_sessions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, "sora-2": { "litellm_provider": "openai", "mode": "video_generation", @@ -42195,4 +42204,105 @@ "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter" } -} \ No newline at end of file +, + "deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 2.8e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "deepseek/deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 2.8e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "deepseek/deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + } +} diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9beb4625be6..b2966f55ab2 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -42417,11 +42417,61 @@ "source": "https://serverless.tensormesh.ai/v1/models/openrouter" } , + "deepseek-v4-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.8e-09, + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 2.8e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "deepseek-v4-pro": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1.4e-08, + "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 1.4e-08, + "input_cost_per_token_cache_hit": 2.8e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 8192, @@ -42444,15 +42494,15 @@ }, "deepseek/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1.74e-07, - "input_cost_per_token": 1.74e-06, - "input_cost_per_token_cache_hit": 1.74e-07, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.48e-06, + "output_cost_per_token": 8.7e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index e4e78971972..96cf9ccfc77 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -889,6 +889,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "/v1/audio/speech", "/v1/ocr", "/vertex_ai/live", + "/v1/realtime/transcription_sessions", ], }, },