diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7fa09951eae..2d8e8071479 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4497,7 +4497,7 @@ }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -4543,7 +4543,7 @@ }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -8730,7 +8730,7 @@ "supports_function_calling": true }, "azure/o1": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", @@ -8748,7 +8748,7 @@ }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8825,7 +8825,7 @@ "supports_vision": false }, "azure/o3": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -8855,7 +8855,7 @@ "supports_vision": true }, "azure/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -8886,7 +8886,7 @@ }, "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-12-26", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8923,7 +8923,7 @@ "supports_web_search": true }, "azure/o3-mini": { - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -8940,7 +8940,7 @@ }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8954,7 +8954,7 @@ "supports_vision": false }, "azure/o3-pro": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -8985,7 +8985,7 @@ "supports_vision": true }, "azure/o3-pro-2025-06-10": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -9016,7 +9016,7 @@ "supports_vision": true }, "azure/o4-mini": { - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -9047,7 +9047,7 @@ }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -9600,7 +9600,7 @@ }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -9645,7 +9645,7 @@ "supports_vision": false }, "azure/us/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "azure", @@ -9676,7 +9676,7 @@ }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -9693,7 +9693,7 @@ }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.1e-07, - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -14615,7 +14615,7 @@ }, "computer-use-preview": { "input_cost_per_token": 3e-06, - "litellm_provider": "azure", + "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, @@ -14633,12 +14633,14 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "source": "https://platform.openai.com/docs/models/computer-use-preview" }, "dall-e-2": { "deprecation_date": "2026-05-12", @@ -39019,7 +39021,9 @@ "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, @@ -39167,18 +39171,20 @@ }, "openrouter/deepseek/deepseek-v3.2": { "input_cost_per_token": 2.69e-07, - "input_cost_per_token_cache_hit": 2.8e-08, + "input_cost_per_token_cache_hit": 1.345e-07, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-v3.2-exp": { "input_cost_per_token": 2.7e-07, @@ -43488,6 +43494,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -43780,6 +43787,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -43794,6 +43802,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -43906,6 +43915,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { + "deprecation_date": "2026-09-14", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -60832,6 +60842,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-08-19", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.5e-06, "cache_read_input_token_cost": 2e-07, @@ -60858,6 +60869,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "together_ai", @@ -60866,6 +60878,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/zai-org/GLM-5.1": { + "deprecation_date": "2026-07-10", "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -60883,6 +60896,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 5e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", @@ -60891,6 +60905,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "together_ai", @@ -60899,6 +60914,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 1.8e-07, "output_cost_per_token": 6.8e-07, "litellm_provider": "together_ai", @@ -60931,6 +60947,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/QwQ-32B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7fa09951eae..2d8e8071479 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4497,7 +4497,7 @@ }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -4543,7 +4543,7 @@ }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -8730,7 +8730,7 @@ "supports_function_calling": true }, "azure/o1": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 7.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", @@ -8748,7 +8748,7 @@ }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 7.5e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8825,7 +8825,7 @@ "supports_vision": false }, "azure/o3": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -8855,7 +8855,7 @@ "supports_vision": true }, "azure/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "azure", @@ -8886,7 +8886,7 @@ }, "azure/o3-deep-research": { "cache_read_input_token_cost": 2.5e-06, - "deprecation_date": "2026-12-26", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8923,7 +8923,7 @@ "supports_web_search": true }, "azure/o3-mini": { - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -8940,7 +8940,7 @@ }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -8954,7 +8954,7 @@ "supports_vision": false }, "azure/o3-pro": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -8985,7 +8985,7 @@ "supports_vision": true }, "azure/o3-pro-2025-06-10": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 2e-05, "input_cost_per_token_batches": 1e-05, "litellm_provider": "azure", @@ -9016,7 +9016,7 @@ "supports_vision": true }, "azure/o4-mini": { - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", @@ -9047,7 +9047,7 @@ }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-07, - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -9600,7 +9600,7 @@ }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -9645,7 +9645,7 @@ "supports_vision": false }, "azure/us/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "litellm_provider": "azure", @@ -9676,7 +9676,7 @@ }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", @@ -9693,7 +9693,7 @@ }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.1e-07, - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -14615,7 +14615,7 @@ }, "computer-use-preview": { "input_cost_per_token": 3e-06, - "litellm_provider": "azure", + "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, @@ -14633,12 +14633,14 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "source": "https://platform.openai.com/docs/models/computer-use-preview" }, "dall-e-2": { "deprecation_date": "2026-05-12", @@ -39019,7 +39021,9 @@ "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, @@ -39167,18 +39171,20 @@ }, "openrouter/deepseek/deepseek-v3.2": { "input_cost_per_token": 2.69e-07, - "input_cost_per_token_cache_hit": 2.8e-08, + "input_cost_per_token_cache_hit": 1.345e-07, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-v3.2-exp": { "input_cost_per_token": 2.7e-07, @@ -43488,6 +43494,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -43780,6 +43787,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -43794,6 +43802,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { + "deprecation_date": "2026-09-14", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -43906,6 +43915,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { + "deprecation_date": "2026-09-14", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -60832,6 +60842,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-08-19", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 4.5e-06, "cache_read_input_token_cost": 2e-07, @@ -60858,6 +60869,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "together_ai", @@ -60866,6 +60878,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/zai-org/GLM-5.1": { + "deprecation_date": "2026-07-10", "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -60883,6 +60896,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 5e-07, "output_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", @@ -60891,6 +60905,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "litellm_provider": "together_ai", @@ -60899,6 +60914,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 1.8e-07, "output_cost_per_token": 6.8e-07, "litellm_provider": "together_ai", @@ -60931,6 +60947,7 @@ "source": "https://api.together.xyz/v1/models" }, "together_ai/Qwen/QwQ-32B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, "litellm_provider": "together_ai",