mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
fix(azure): correct GPT-5.5 dated variants to Azure snapshot 2026-04-24
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
milan
parent
7015bd2ea1
commit
871e035130
4 changed files with 281 additions and 77 deletions
|
|
@ -2973,7 +2973,7 @@
|
|||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure_ai/gpt-5.5-2026-04-23": {
|
||||
"azure_ai/gpt-5.5-2026-04-24": {
|
||||
"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,
|
||||
|
|
@ -6752,7 +6752,7 @@
|
|||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-2026-04-23": {
|
||||
"azure/gpt-5.5-2026-04-24": {
|
||||
"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,
|
||||
|
|
@ -6792,9 +6792,12 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/us/gpt-5.5-2026-04-23": {
|
||||
"azure/us/gpt-5.5-2026-04-24": {
|
||||
"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": 1.38e-06,
|
||||
|
|
@ -6831,9 +6834,12 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/eu/gpt-5.5-2026-04-23": {
|
||||
"azure/eu/gpt-5.5-2026-04-24": {
|
||||
"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": 1.38e-06,
|
||||
|
|
@ -6870,7 +6876,10 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-pro": {
|
||||
"cache_read_input_token_cost": 3e-06,
|
||||
|
|
@ -6911,7 +6920,7 @@
|
|||
"supports_minimal_reasoning_effort": false,
|
||||
"supports_low_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-pro-2026-04-23": {
|
||||
"azure/gpt-5.5-pro-2026-04-24": {
|
||||
"cache_read_input_token_cost": 3e-06,
|
||||
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
|
||||
"input_cost_per_token": 3e-05,
|
||||
|
|
@ -6944,7 +6953,11 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": false,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false,
|
||||
"supports_low_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.4-mini": {
|
||||
"cache_read_input_token_cost": 7.5e-08,
|
||||
|
|
@ -17381,6 +17394,46 @@
|
|||
"tpm": 8000000,
|
||||
"supports_image_size": false
|
||||
},
|
||||
"gemini-3-pro-image": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
"input_cost_per_token_batches": 1e-06,
|
||||
"litellm_provider": "vertex_ai-language-models",
|
||||
"max_input_tokens": 65536,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "image_generation",
|
||||
"output_cost_per_image": 0.134,
|
||||
"output_cost_per_image_token": 0.00012,
|
||||
"output_cost_per_token": 1.2e-05,
|
||||
"output_cost_per_token_batches": 6e-06,
|
||||
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
|
||||
"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": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true,
|
||||
"search_context_cost_per_query": {
|
||||
"search_context_size_low": 0.014,
|
||||
"search_context_size_medium": 0.014,
|
||||
"search_context_size_high": 0.014
|
||||
},
|
||||
"web_search_billing_unit": "per_query"
|
||||
},
|
||||
"gemini-3-pro-image-preview": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
|
|
@ -17421,6 +17474,44 @@
|
|||
},
|
||||
"web_search_billing_unit": "per_query"
|
||||
},
|
||||
"gemini-3.1-flash-image": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 5e-07,
|
||||
"litellm_provider": "vertex_ai-language-models",
|
||||
"max_input_tokens": 65536,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "image_generation",
|
||||
"output_cost_per_image": 0.0672,
|
||||
"output_cost_per_image_token": 6e-05,
|
||||
"output_cost_per_token": 3e-06,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
|
||||
"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": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true,
|
||||
"search_context_cost_per_query": {
|
||||
"search_context_size_low": 0.014,
|
||||
"search_context_size_medium": 0.014,
|
||||
"search_context_size_high": 0.014
|
||||
},
|
||||
"web_search_billing_unit": "per_query"
|
||||
},
|
||||
"gemini-3.1-flash-image-preview": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 5e-07,
|
||||
|
|
@ -18866,7 +18957,6 @@
|
|||
],
|
||||
"supports_function_calling": false,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": false,
|
||||
"supports_response_schema": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_vision": true,
|
||||
|
|
@ -18876,7 +18966,8 @@
|
|||
"search_context_size_medium": 0.014,
|
||||
"search_context_size_high": 0.014
|
||||
},
|
||||
"web_search_billing_unit": "per_query"
|
||||
"web_search_billing_unit": "per_query",
|
||||
"supports_reasoning": false
|
||||
},
|
||||
"gemini/gemini-3-pro-image-preview": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
|
|
@ -20312,8 +20403,7 @@
|
|||
"max_tokens": 16000,
|
||||
"mode": "chat",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions",
|
||||
"/v1/messages"
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
|
|
@ -20326,8 +20416,7 @@
|
|||
"max_tokens": 16000,
|
||||
"mode": "chat",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions",
|
||||
"/v1/messages"
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
|
|
@ -20379,8 +20468,7 @@
|
|||
"max_tokens": 16000,
|
||||
"mode": "chat",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions",
|
||||
"/v1/messages"
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
|
|
@ -23672,7 +23760,7 @@
|
|||
"input_cost_per_token_batches": 3.75e-07,
|
||||
"input_cost_per_token_priority": 1.5e-06,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 272000,
|
||||
"max_input_tokens": 1050000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "chat",
|
||||
|
|
@ -23718,7 +23806,7 @@
|
|||
"input_cost_per_token_batches": 3.75e-07,
|
||||
"input_cost_per_token_priority": 1.5e-06,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 272000,
|
||||
"max_input_tokens": 1050000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "chat",
|
||||
|
|
@ -23762,7 +23850,7 @@
|
|||
"input_cost_per_token_flex": 1e-07,
|
||||
"input_cost_per_token_batches": 1e-07,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 272000,
|
||||
"max_input_tokens": 1050000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "chat",
|
||||
|
|
@ -23805,7 +23893,7 @@
|
|||
"input_cost_per_token_flex": 1e-07,
|
||||
"input_cost_per_token_batches": 1e-07,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 272000,
|
||||
"max_input_tokens": 1050000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "chat",
|
||||
|
|
@ -23845,9 +23933,9 @@
|
|||
"input_cost_per_token": 1.5e-05,
|
||||
"input_cost_per_token_batches": 7.5e-06,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 128000,
|
||||
"max_output_tokens": 272000,
|
||||
"max_tokens": 272000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "responses",
|
||||
"output_cost_per_token": 0.00012,
|
||||
"output_cost_per_token_batches": 6e-05,
|
||||
|
|
@ -23881,9 +23969,9 @@
|
|||
"input_cost_per_token": 1.5e-05,
|
||||
"input_cost_per_token_batches": 7.5e-06,
|
||||
"litellm_provider": "openai",
|
||||
"max_input_tokens": 128000,
|
||||
"max_output_tokens": 272000,
|
||||
"max_tokens": 272000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_output_tokens": 128000,
|
||||
"max_tokens": 128000,
|
||||
"mode": "responses",
|
||||
"output_cost_per_token": 0.00012,
|
||||
"output_cost_per_token_batches": 6e-05,
|
||||
|
|
@ -31246,6 +31334,22 @@
|
|||
"supports_reasoning": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"openrouter/z-ai/glm-5.1": {
|
||||
"input_cost_per_token": 1.05e-06,
|
||||
"output_cost_per_token": 3.5e-06,
|
||||
"cache_read_input_token_cost": 5.25e-07,
|
||||
"cache_creation_input_token_cost": 0.0,
|
||||
"litellm_provider": "openrouter",
|
||||
"max_input_tokens": 202752,
|
||||
"max_output_tokens": 65535,
|
||||
"max_tokens": 65535,
|
||||
"mode": "chat",
|
||||
"source": "https://openrouter.ai/z-ai/glm-5.1",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"openrouter/minimax/minimax-m2.1": {
|
||||
"input_cost_per_token": 2.7e-07,
|
||||
"output_cost_per_token": 1.2e-06,
|
||||
|
|
@ -39395,6 +39499,21 @@
|
|||
"supports_tool_choice": true,
|
||||
"source": "https://docs.z.ai/guides/overview/pricing"
|
||||
},
|
||||
"zai/glm-5.1": {
|
||||
"cache_creation_input_token_cost": 0,
|
||||
"cache_read_input_token_cost": 2.6e-07,
|
||||
"input_cost_per_token": 1.4e-06,
|
||||
"output_cost_per_token": 4.4e-06,
|
||||
"litellm_provider": "zai",
|
||||
"max_input_tokens": 200000,
|
||||
"max_output_tokens": 128000,
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_tool_choice": true,
|
||||
"source": "https://docs.z.ai/guides/overview/pricing"
|
||||
},
|
||||
"zai/glm-5-code": {
|
||||
"cache_creation_input_token_cost": 0,
|
||||
"cache_read_input_token_cost": 3e-07,
|
||||
|
|
@ -39425,6 +39544,21 @@
|
|||
"supports_tool_choice": true,
|
||||
"source": "https://docs.z.ai/guides/overview/pricing"
|
||||
},
|
||||
"zai/glm-4.7-flash": {
|
||||
"cache_creation_input_token_cost": 0,
|
||||
"cache_read_input_token_cost": 0,
|
||||
"input_cost_per_token": 0,
|
||||
"output_cost_per_token": 0,
|
||||
"litellm_provider": "zai",
|
||||
"max_input_tokens": 200000,
|
||||
"max_output_tokens": 128000,
|
||||
"mode": "chat",
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_tool_choice": true,
|
||||
"source": "https://docs.z.ai/guides/overview/pricing"
|
||||
},
|
||||
"zai/glm-4.6": {
|
||||
"cache_creation_input_token_cost": 0,
|
||||
"cache_read_input_token_cost": 1.1e-07,
|
||||
|
|
@ -44835,6 +44969,7 @@
|
|||
"supports_response_schema": true
|
||||
},
|
||||
"snowflake/claude-sonnet-4-6": {
|
||||
"supports_adaptive_thinking": true,
|
||||
"max_tokens": 16384,
|
||||
"max_input_tokens": 200000,
|
||||
"max_output_tokens": 16384,
|
||||
|
|
@ -45253,40 +45388,6 @@
|
|||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"darkbloom/gemma-4-26b": {
|
||||
"input_cost_per_token": 3e-08,
|
||||
"litellm_provider": "darkbloom",
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 1.65e-07,
|
||||
"source": "https://www.darkbloom.dev/",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"darkbloom/gpt-oss-20b": {
|
||||
"input_cost_per_token": 1.45e-08,
|
||||
"litellm_provider": "darkbloom",
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 7e-08,
|
||||
"source": "https://www.darkbloom.dev/",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"deepseek/deepseek-v4-pro": {
|
||||
"cache_creation_input_token_cost": 0.0,
|
||||
"cache_read_input_token_cost": 3.625e-09,
|
||||
|
|
@ -45442,6 +45543,40 @@
|
|||
"supports_reasoning": false,
|
||||
"source": "https://pinstripes.io/pricing"
|
||||
},
|
||||
"darkbloom/gemma-4-26b": {
|
||||
"input_cost_per_token": 3e-08,
|
||||
"litellm_provider": "darkbloom",
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 1.65e-07,
|
||||
"source": "https://www.darkbloom.dev/",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"darkbloom/gpt-oss-20b": {
|
||||
"input_cost_per_token": 1.45e-08,
|
||||
"litellm_provider": "darkbloom",
|
||||
"max_input_tokens": 131072,
|
||||
"max_output_tokens": 32768,
|
||||
"max_tokens": 32768,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 7e-08,
|
||||
"source": "https://www.darkbloom.dev/",
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"fallback_generalizations": {
|
||||
"rules": [
|
||||
{
|
||||
|
|
|
|||
|
|
@ -2973,7 +2973,7 @@
|
|||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure_ai/gpt-5.5-2026-04-23": {
|
||||
"azure_ai/gpt-5.5-2026-04-24": {
|
||||
"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,
|
||||
|
|
@ -6752,7 +6752,7 @@
|
|||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-2026-04-23": {
|
||||
"azure/gpt-5.5-2026-04-24": {
|
||||
"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,
|
||||
|
|
@ -6792,9 +6792,12 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/us/gpt-5.5-2026-04-23": {
|
||||
"azure/us/gpt-5.5-2026-04-24": {
|
||||
"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": 1.38e-06,
|
||||
|
|
@ -6831,9 +6834,12 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/eu/gpt-5.5-2026-04-23": {
|
||||
"azure/eu/gpt-5.5-2026-04-24": {
|
||||
"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": 1.38e-06,
|
||||
|
|
@ -6870,7 +6876,10 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": true,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-pro": {
|
||||
"cache_read_input_token_cost": 3e-06,
|
||||
|
|
@ -6911,7 +6920,7 @@
|
|||
"supports_minimal_reasoning_effort": false,
|
||||
"supports_low_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.5-pro-2026-04-23": {
|
||||
"azure/gpt-5.5-pro-2026-04-24": {
|
||||
"cache_read_input_token_cost": 3e-06,
|
||||
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
|
||||
"input_cost_per_token": 3e-05,
|
||||
|
|
@ -6944,7 +6953,11 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
"supports_web_search": true,
|
||||
"supports_none_reasoning_effort": false,
|
||||
"supports_xhigh_reasoning_effort": true,
|
||||
"supports_minimal_reasoning_effort": false,
|
||||
"supports_low_reasoning_effort": false
|
||||
},
|
||||
"azure/gpt-5.4-mini": {
|
||||
"cache_read_input_token_cost": 7.5e-08,
|
||||
|
|
|
|||
|
|
@ -786,9 +786,11 @@ def test_gpt55_dated_variants_match_base_reasoning_effort_capabilities(
|
|||
"model,expected_mode,expected_input,expected_output,expected_cache_read",
|
||||
[
|
||||
("azure/gpt-5.5", "chat", 5e-6, 3e-5, 5e-7),
|
||||
("azure/gpt-5.5-2026-04-23", "chat", 5e-6, 3e-5, 5e-7),
|
||||
# Azure's GPT-5.5 snapshot is 2026-04-24 (OpenAI's is 2026-04-23); the
|
||||
# Azure dated deployment string must use Azure's version, not OpenAI's.
|
||||
("azure/gpt-5.5-2026-04-24", "chat", 5e-6, 3e-5, 5e-7),
|
||||
("azure/gpt-5.5-pro", "responses", 3e-5, 1.8e-4, 3e-6),
|
||||
("azure/gpt-5.5-pro-2026-04-23", "responses", 3e-5, 1.8e-4, 3e-6),
|
||||
("azure/gpt-5.5-pro-2026-04-24", "responses", 3e-5, 1.8e-4, 3e-6),
|
||||
],
|
||||
)
|
||||
def test_azure_gpt55_entries_present_with_correct_pricing(
|
||||
|
|
@ -839,6 +841,51 @@ def test_azure_gpt55_reasoning_effort_flags_match_live_openai_api(
|
|||
assert m.get("supports_xhigh_reasoning_effort") is expected_xhigh
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"base_model,dated_model",
|
||||
[
|
||||
("azure/gpt-5.5", "azure/gpt-5.5-2026-04-24"),
|
||||
("azure/us/gpt-5.5", "azure/us/gpt-5.5-2026-04-24"),
|
||||
("azure/eu/gpt-5.5", "azure/eu/gpt-5.5-2026-04-24"),
|
||||
("azure_ai/gpt-5.5", "azure_ai/gpt-5.5-2026-04-24"),
|
||||
("azure/gpt-5.5-pro", "azure/gpt-5.5-pro-2026-04-24"),
|
||||
],
|
||||
)
|
||||
def test_azure_gpt55_dated_variant_uses_azure_snapshot_and_matches_base(
|
||||
base_model, dated_model
|
||||
):
|
||||
"""Azure GPT-5.5 dated deployments use Azure's 2026-04-24 snapshot.
|
||||
|
||||
The Azure GPT-5.5 family ships as version 2026-04-24 (OpenAI's snapshot is
|
||||
2026-04-23); the day-0 entries wrongly copied OpenAI's date. Guard that the
|
||||
OpenAI-dated Azure keys never come back, that the Azure-dated keys exist,
|
||||
and that pinning a dated Azure variant keeps the exact reasoning_effort
|
||||
capability profile of its floating alias.
|
||||
"""
|
||||
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
|
||||
litellm.model_cost = litellm.get_model_cost_map(url="")
|
||||
|
||||
wrong_dated = dated_model.replace("2026-04-24", "2026-04-23")
|
||||
assert (
|
||||
wrong_dated not in litellm.model_cost
|
||||
), f"{wrong_dated} uses OpenAI's snapshot date; Azure ships 2026-04-24"
|
||||
assert dated_model in litellm.model_cost, f"{dated_model} missing from cost map"
|
||||
|
||||
base = litellm.model_cost[base_model]
|
||||
dated = litellm.model_cost[dated_model]
|
||||
for flag in (
|
||||
"supports_none_reasoning_effort",
|
||||
"supports_minimal_reasoning_effort",
|
||||
"supports_xhigh_reasoning_effort",
|
||||
"supports_low_reasoning_effort",
|
||||
):
|
||||
assert dated.get(flag) == base.get(flag), (
|
||||
f"{dated_model} has {flag}={dated.get(flag)!r}, but {base_model} "
|
||||
f"has {flag}={base.get(flag)!r}. Dated Azure snapshots must inherit "
|
||||
f"the base model's reasoning_effort capability profile."
|
||||
)
|
||||
|
||||
|
||||
def test_generic_cost_per_token_anthropic_prompt_caching():
|
||||
model = "claude-sonnet-4@20250514"
|
||||
usage = Usage(
|
||||
|
|
|
|||
|
|
@ -6,8 +6,18 @@ import pytest
|
|||
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", ["azure_ai/gpt-5.5", "azure_ai/gpt-5.5-2026-04-23"])
|
||||
def test_azure_ai_gpt_5_5_model_info(model):
|
||||
@pytest.mark.parametrize(
|
||||
"model,expected_provider",
|
||||
[
|
||||
# gpt-5.5 is a known OpenAI model name, so azure_ai/gpt-5.5 is routed
|
||||
# through the Azure OpenAI path (custom_llm_provider="azure").
|
||||
("azure_ai/gpt-5.5", "azure"),
|
||||
# 2026-04-24 is Azure's own GPT-5.5 snapshot (OpenAI's is 2026-04-23),
|
||||
# so it is not an OpenAI model name and stays on the azure_ai path.
|
||||
("azure_ai/gpt-5.5-2026-04-24", "azure_ai"),
|
||||
],
|
||||
)
|
||||
def test_azure_ai_gpt_5_5_model_info(model, expected_provider):
|
||||
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
|
||||
with open(json_path) as f:
|
||||
model_cost = json.load(f)
|
||||
|
|
@ -47,8 +57,7 @@ def test_azure_ai_gpt_5_5_model_info(model):
|
|||
|
||||
routed_model, provider, _, _ = get_llm_provider(model=model)
|
||||
assert routed_model == model.split("/", 1)[1]
|
||||
# azure_ai/* models resolve under the azure provider in get_llm_provider
|
||||
assert provider == "azure"
|
||||
assert provider == expected_provider
|
||||
|
||||
|
||||
def test_azure_ai_gpt_5_5_backup_matches_main():
|
||||
|
|
@ -62,7 +71,7 @@ def test_azure_ai_gpt_5_5_backup_matches_main():
|
|||
with open(backup_path) as f:
|
||||
backup_cost = json.load(f)
|
||||
|
||||
for model in ("azure_ai/gpt-5.5", "azure_ai/gpt-5.5-2026-04-23"):
|
||||
for model in ("azure_ai/gpt-5.5", "azure_ai/gpt-5.5-2026-04-24"):
|
||||
assert backup_cost.get(model) == main_cost.get(
|
||||
model
|
||||
), f"{model} differs between main and backup model cost maps"
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue