From f90b3efb2e2a737324769ce28f2a4b556ce207cb Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 9 Jul 2026 20:46:21 -0700 Subject: [PATCH] feat(models): add Azure GPT-5.6 (sol/terra/luna) pricing and metadata (#32678) --- ...odel_prices_and_context_window_backup.json | 516 ++++++++++++++++++ model_prices_and_context_window.json | 516 ++++++++++++++++++ .../llm_cost_calc/test_llm_cost_calc_utils.py | 43 ++ .../test_gpt_5_6_model_metadata.py | 73 ++- 4 files changed, 1147 insertions(+), 1 deletion(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 8be2e5d01c5..2a269d693ec 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -6012,6 +6012,522 @@ "supports_vision": true, "supports_web_search": true }, + "azure/gpt-5.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "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, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-sol": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "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, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-luna": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "input_cost_per_token_priority": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "output_cost_per_token_priority": 1.2e-05, + "output_cost_per_token_above_272k_tokens_priority": 1.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-sol": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_priority": 6.875e-07, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_priority": 6.875e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_priority": 4.125e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-luna": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_above_272k_tokens": 9.9e-06, + "output_cost_per_token_priority": 1.65e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-sol": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_priority": 6.875e-07, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_priority": 6.875e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_priority": 4.125e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-luna": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_above_272k_tokens": 9.9e-06, + "output_cost_per_token_priority": 1.65e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 08456386362..e79ddbe35d2 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -6012,6 +6012,522 @@ "supports_vision": true, "supports_web_search": true }, + "azure/gpt-5.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "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, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-sol": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "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, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_priority": 4.5e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-luna": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "input_cost_per_token_priority": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_272k_tokens": 9e-06, + "output_cost_per_token_priority": 1.2e-05, + "output_cost_per_token_above_272k_tokens_priority": 1.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-sol": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_priority": 6.875e-07, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_priority": 6.875e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_priority": 4.125e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/us/gpt-5.6-luna": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_above_272k_tokens": 9.9e-06, + "output_cost_per_token_priority": 1.65e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-sol": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-terra": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_read_input_token_cost_priority": 6.875e-07, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_priority": 6.875e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_priority": 4.125e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/eu/gpt-5.6-luna": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_above_272k_tokens": 2.2e-06, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_above_272k_tokens": 9.9e-06, + "output_cost_per_token_priority": 1.65e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/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_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.5": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, 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 dcc359ceff4..ca23e61352e 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 @@ -562,6 +562,49 @@ def test_generic_cost_per_token_gpt56( assert round(completion_cost, 10) == round(output_cost * completion_tokens, 10) +@pytest.mark.parametrize( + "model,input_cost,output_cost,cache_read_cost", + [ + ("azure/gpt-5.6", 5e-6, 3e-5, 5e-7), + ("azure/gpt-5.6-sol", 5e-6, 3e-5, 5e-7), + ("azure/gpt-5.6-terra", 2.5e-6, 1.5e-5, 2.5e-7), + ("azure/gpt-5.6-luna", 1e-6, 6e-6, 1e-7), + ("azure/us/gpt-5.6", 5.5e-6, 3.3e-5, 5.5e-7), + ("azure/eu/gpt-5.6-terra", 2.75e-6, 1.65e-5, 2.75e-7), + ("azure/eu/gpt-5.6-luna", 1.1e-6, 6.6e-6, 1.1e-7), + ], +) +def test_generic_cost_per_token_azure_gpt56( + model, input_cost, output_cost, cache_read_cost +): + """Azure gpt-5.6 (global + us/eu regional): pricing mirrors the openai + family for global deployments and carries the standard 10% regional uplift. + """ + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + model_cost_map = litellm.model_cost[model] + assert model_cost_map["litellm_provider"] == "azure" + assert model_cost_map["input_cost_per_token"] == input_cost + assert model_cost_map["output_cost_per_token"] == output_cost + assert model_cost_map["cache_read_input_token_cost"] == cache_read_cost + + prompt_tokens = 1000 + completion_tokens = 500 + usage = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + ) + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider="azure", + ) + assert round(prompt_cost, 10) == round(input_cost * prompt_tokens, 10) + assert round(completion_cost, 10) == round(output_cost * completion_tokens, 10) + + @pytest.mark.parametrize( "model,expected_none,expected_xhigh,expected_minimal", [ diff --git a/tests/test_litellm/test_gpt_5_6_model_metadata.py b/tests/test_litellm/test_gpt_5_6_model_metadata.py index 30a0777f477..af9bb117f78 100644 --- a/tests/test_litellm/test_gpt_5_6_model_metadata.py +++ b/tests/test_litellm/test_gpt_5_6_model_metadata.py @@ -62,6 +62,77 @@ def test_openai_gpt_5_6_model_info(model): assert provider == "openai" +AZURE_GLOBAL_MODELS = ( + "azure/gpt-5.6", + "azure/gpt-5.6-sol", + "azure/gpt-5.6-terra", + "azure/gpt-5.6-luna", +) + +AZURE_REGIONAL_MODELS = tuple( + f"azure/{region}/{tier}" + for region in ("us", "eu") + for tier in ("gpt-5.6", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna") +) + + +def _tier_key(azure_model): + return azure_model.split("/")[-1] + + +def _load_main(): + json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json" + with open(json_path) as f: + return json.load(f) + + +@pytest.mark.parametrize("model", AZURE_GLOBAL_MODELS) +def test_azure_gpt_5_6_global_model_info(model): + model_cost = _load_main() + info = model_cost.get(model) + assert info is not None, f"{model} not found in model_prices_and_context_window.json" + + assert info["litellm_provider"] == "azure" + assert info["mode"] == "chat" + + input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)] + assert info["input_cost_per_token"] == input_cost + assert info["output_cost_per_token"] == output_cost + assert info["cache_read_input_token_cost"] == cache_read_cost + + assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2) + assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.5) + assert info["input_cost_per_token_priority"] == pytest.approx(input_cost * 2) + assert info["output_cost_per_token_priority"] == pytest.approx(output_cost * 2) + assert info["input_cost_per_token_above_272k_tokens_priority"] == pytest.approx(input_cost * 4) + assert info["output_cost_per_token_above_272k_tokens_priority"] == pytest.approx(output_cost * 3) + + assert info["max_input_tokens"] == 1050000 + assert info["max_output_tokens"] == 128000 + assert info["supports_reasoning"] is True + + routed_model, provider, _, _ = get_llm_provider(model=model) + assert provider == "azure" + + +@pytest.mark.parametrize("model", AZURE_REGIONAL_MODELS) +def test_azure_gpt_5_6_regional_model_info(model): + model_cost = _load_main() + info = model_cost.get(model) + assert info is not None, f"{model} not found in model_prices_and_context_window.json" + + assert info["litellm_provider"] == "azure" + input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)] + + assert info["input_cost_per_token"] == pytest.approx(input_cost * 1.1) + assert info["output_cost_per_token"] == pytest.approx(output_cost * 1.1) + assert info["cache_read_input_token_cost"] == pytest.approx(cache_read_cost * 1.1) + assert info["input_cost_per_token_above_272k_tokens"] == pytest.approx(input_cost * 2.2) + assert info["output_cost_per_token_above_272k_tokens"] == pytest.approx(output_cost * 1.65) + assert info["input_cost_per_token_priority"] == pytest.approx(input_cost * 2.75) + assert info["output_cost_per_token_priority"] == pytest.approx(output_cost * 2.75) + + def test_gpt_5_6_backup_matches_main(): """Ensure the bundled model cost map stays in sync with the canonical file.""" repo_root = Path(__file__).parents[2] @@ -73,7 +144,7 @@ def test_gpt_5_6_backup_matches_main(): with open(backup_path) as f: backup_cost = json.load(f) - for model in GPT_5_6_MODELS: + for model in GPT_5_6_MODELS + AZURE_GLOBAL_MODELS + AZURE_REGIONAL_MODELS: assert backup_cost.get(model) == main_cost.get(model), ( f"{model} differs between main and backup model cost maps" )