scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-03 02:22:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

feat(cost-map): add Azure Foundry pricing for gpt-6-sol and gpt-6-luna (#42747)

Browse source 
* feat(cost-map): add Azure Foundry pricing for gpt-6-sol and gpt-6-luna

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(cost-map): give azure/eu gpt-6-sol and gpt-6-luna full model metadata

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-23 15:17:36 +00:00 • committed by GitHub
parent 48050d9646
commit 6b642f3648
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 1019 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

482
litellm/model_prices_and_context_window_backup.json
View file

@ -3810,6 +3810,104 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure_ai/gpt-6-luna": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_cache_breakpoint": 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_xhigh_reasoning_effort": true
},
"azure_ai/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_cache_breakpoint": 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_xhigh_reasoning_effort": true
},
"azure_ai/gpt-5.5": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
@ -7800,6 +7898,198 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/gpt-6-luna": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-luna-2026-09-22": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-sol-2026-09-22": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
@ -8144,6 +8434,102 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/us/gpt-6-luna": {
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-07,
"cache_read_input_token_cost": 1.1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_above_272k_tokens": 2.2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.5e-07,
"output_cost_per_token_above_272k_tokens": 8.25e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/us/gpt-6-sol": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_above_272k_tokens": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/us/gpt-chat-latest": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-12-02",
@ -66754,6 +67140,102 @@
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/gpt-6-luna": {
"cache_creation_input_token_cost": 1.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 3e-07,
"cache_read_input_token_cost": 1.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 2.4e-08,
"input_cost_per_token": 1.2e-07,
"input_cost_per_token_above_272k_tokens": 2.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token_above_272k_tokens": 9e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/eu/gpt-6-sol": {
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost": 2.4e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.8e-07,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_above_272k_tokens": 4.8e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/eu/o1-mini": {
"cache_read_input_token_cost": 6.05e-07,
"input_cost_per_token": 1.21e-06,

482
model_prices_and_context_window.json
View file

@ -3810,6 +3810,104 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure_ai/gpt-6-luna": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_cache_breakpoint": 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_xhigh_reasoning_effort": true
},
"azure_ai/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_cache_breakpoint": 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_xhigh_reasoning_effort": true
},
"azure_ai/gpt-5.5": {
"deprecation_date": "2027-10-26",
"cache_read_input_token_cost": 5e-07,
@ -7800,6 +7898,198 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/gpt-6-luna": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-luna-2026-09-22": {
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_above_272k_tokens": 2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token_above_272k_tokens": 7.5e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-sol": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-6-sol-2026-09-22": {
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_above_272k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/gpt-chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
@ -8144,6 +8434,102 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/us/gpt-6-luna": {
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-07,
"cache_read_input_token_cost": 1.1e-08,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-08,
"input_cost_per_token": 1.1e-07,
"input_cost_per_token_above_272k_tokens": 2.2e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.5e-07,
"output_cost_per_token_above_272k_tokens": 8.25e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/us/gpt-6-sol": {
"cache_creation_input_token_cost": 2.75e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
"cache_read_input_token_cost": 2.2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_above_272k_tokens": 4.4e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_above_272k_tokens": 1.65e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/us/gpt-chat-latest": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-12-02",
@ -66754,6 +67140,102 @@
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/gpt-6-luna": {
"cache_creation_input_token_cost": 1.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 3e-07,
"cache_read_input_token_cost": 1.2e-08,
"cache_read_input_token_cost_above_272k_tokens": 2.4e-08,
"input_cost_per_token": 1.2e-07,
"input_cost_per_token_above_272k_tokens": 2.4e-07,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token_above_272k_tokens": 9e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/eu/gpt-6-sol": {
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost": 2.4e-07,
"cache_read_input_token_cost_above_272k_tokens": 4.8e-07,
"input_cost_per_token": 2.4e-06,
"input_cost_per_token_above_272k_tokens": 4.8e-06,
"litellm_provider": "azure",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true
},
"azure/eu/o1-mini": {
"cache_read_input_token_cost": 6.05e-07,
"input_cost_per_token": 1.21e-06,

28
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -3761,3 +3761,31 @@ def test_get_batch_cost_rates_has_no_cache_write_rate_without_a_cache_write_batc
)
assert rates.cache_creation is None
@pytest.mark.parametrize("model_base", ["gpt-6-sol", "gpt-6-luna"])
def test_azure_gpt_6_foundry_price_sheet(_local_model_cost_map, model_base):
"""Azure Foundry hosts gpt-6-sol and gpt-6-luna at OpenAI's Global rates, with the
US and EU data zones charging fixed uplifts on top of them."""
price_fields = (
"input_cost_per_token",
"cache_read_input_token_cost",
"cache_creation_input_token_cost",
"output_cost_per_token",
"input_cost_per_token_above_272k_tokens",
"cache_read_input_token_cost_above_272k_tokens",
"cache_creation_input_token_cost_above_272k_tokens",
"output_cost_per_token_above_272k_tokens",
)
openai_info = litellm.get_model_info(model=model_base, custom_llm_provider="openai")
azure_info = litellm.get_model_info(model=f"azure/{model_base}", custom_llm_provider="azure")
azure_us_info = litellm.get_model_info(model=f"azure/us/{model_base}", custom_llm_provider="azure")
azure_eu_info = litellm.get_model_info(model=f"azure/eu/{model_base}", custom_llm_provider="azure")
azure_ai_info = litellm.get_model_info(model=f"azure_ai/{model_base}", custom_llm_provider="azure_ai")
for field in price_fields:
base = openai_info[field]
assert azure_info[field] == base
assert azure_ai_info[field] == base
assert azure_us_info[field] == pytest.approx(1.1 * base)
assert azure_eu_info[field] == pytest.approx(1.2 * base)

27
tests/test_litellm/router_utils/test_reasoning_effort_capability.py
View file

@ -458,3 +458,30 @@ class TestNearestDeclaredReasoningEffort:
def test_a_level_outside_the_strength_order_is_left_for_upstream(self):
assert nearest_declared_reasoning_effort("turbo", ("none", "high")) == "turbo"
assert nearest_declared_reasoning_effort("medium", ()) == "medium"
class TestAzureGpt6SolAndLunaAdvertiseTheOpenAiLevels:
@pytest.mark.parametrize(
"model,custom_llm_provider",
[
("azure/gpt-6-sol", "azure"),
("azure/gpt-6-luna", "azure"),
("azure/eu/gpt-6-sol", "azure"),
("azure/eu/gpt-6-luna", "azure"),
("azure_ai/gpt-6-sol", "azure_ai"),
("azure_ai/gpt-6-luna", "azure_ai"),
],
)
def test_the_azure_entry_advertises_the_same_levels_as_openai(
self, local_model_cost_map, model, custom_llm_provider
):
"""The Foundry deployments of sol and luna take the same effort set OpenAI documents for
the direct API, so the resolved levels must match the OpenAI-direct entry."""
from litellm.utils import _get_model_info_helper
azure_info = dict(_get_model_info_helper(model=model, custom_llm_provider=custom_llm_provider))
openai_info = dict(_get_model_info_helper(model=model.rsplit("/", 1)[1], custom_llm_provider="openai"))
assert resolve_supported_reasoning_efforts(
azure_info, deployment_is_mapped=True
) == resolve_supported_reasoning_efforts(openai_info, deployment_is_mapped=True)