scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-28 06:23:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 94

fix(cost-map): registry audit 2026-10-20, add volcengine doubao-seed-2-1 260915 rows and undated azure data zone rows (#47561)

Browse source 
* fix(cost-map): add volcengine doubao-seed-2-1-pro-260915 and doubao-seed-2-1-lite-260915

Pro row absorbed from #47372, lite row added from the same Volcengine Ark pricing and model list docs

Co-authored-by: donghongfei <1247543758@qq.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(cost-map): cover volcengine doubao-seed-2-1-pro-260915 row

Co-authored-by: donghongfei <1247543758@qq.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(cost-map): add undated azure/eu and azure/us rows for o1, o3, o3-mini, o4-mini, gpt-4o, gpt-4o-mini

Absorbed from #47499

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

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: donghongfei <1247543758@qq.com>
This commit is contained in:
devin-ai-integration[bot] 2026-10-20 06:51:05 -07:00 • committed by GitHub
parent dd20bb0ae9
commit 4818b767d8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 595 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

269
litellm/model_prices_and_context_window_backup.json
View file

@ -4916,6 +4916,26 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
"cache_read_input_token_cost": 1.375e-06,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_batches": 5.5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-2024-11-20": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
@ -4936,6 +4956,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-mini": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"input_cost_per_token_batches": 8.3e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6.6e-07,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
@ -5247,6 +5286,25 @@
"supports_vision": true,
"cache_read_input_token_cost_batches": 2.75e-09
},
"azure/eu/o1": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"output_cost_per_token_batches": 3.3e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/o1-2024-12-17": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
@ -5283,6 +5341,24 @@
"supports_prompt_caching": true,
"supports_vision": false
},
"azure/eu/o3-mini": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/eu/o3-mini-2025-01-31": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
@ -11540,6 +11616,26 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
"cache_read_input_token_cost": 1.375e-06,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_batches": 5.5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-2024-11-20": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
@ -11560,6 +11656,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-mini": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"input_cost_per_token_batches": 8.3e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6.6e-07,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
@ -11871,6 +11986,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o1": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"output_cost_per_token_batches": 3.3e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o1-2024-12-17": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
@ -11907,6 +12041,39 @@
"supports_prompt_caching": true,
"supports_vision": false
},
"azure/us/o3": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_batches": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8.8e-06,
"output_cost_per_token_batches": 4.4e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o3-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
@ -11940,6 +12107,24 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o3-mini": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us/o3-mini-2025-01-31": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
@ -11958,6 +12143,27 @@
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us/o4-mini": {
"cache_read_input_token_cost": 3.03e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o4-mini-2025-04-16": {
"cache_read_input_token_cost": 3.03e-07,
"deprecation_date": "2026-11-19",
@ -61148,6 +61354,41 @@
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-pro-260915": {
"cache_read_input_token_cost": 1.725e-07,
"input_cost_per_token": 8.625e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 1024000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4.3125e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-lite-260915": {
"cache_read_input_audio_token_cost": 3.45e-07,
"cache_read_input_token_cost": 2.3e-08,
"input_cost_per_audio_token": 1.725e-06,
"input_cost_per_token": 1.15e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 1024000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 3.88126e-07,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-turbo-260628": {
"cache_read_input_token_cost": 8.625e-08,
"input_cost_per_token": 4.3125e-07,
@ -70141,6 +70382,20 @@
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o3": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_batches": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8.8e-06,
"output_cost_per_token_batches": 4.4e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o3-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
@ -70164,6 +70419,20 @@
"output_cost_per_token": 4.4e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o4-mini": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 3.03e-07,
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o4-mini-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 3.03e-07,

269
model_prices_and_context_window.json
View file

@ -4916,6 +4916,26 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
"cache_read_input_token_cost": 1.375e-06,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_batches": 5.5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-2024-11-20": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
@ -4936,6 +4956,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-mini": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"input_cost_per_token_batches": 8.3e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6.6e-07,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
@ -5247,6 +5286,25 @@
"supports_vision": true,
"cache_read_input_token_cost_batches": 2.75e-09
},
"azure/eu/o1": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"output_cost_per_token_batches": 3.3e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/eu/o1-2024-12-17": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
@ -5283,6 +5341,24 @@
"supports_prompt_caching": true,
"supports_vision": false
},
"azure/eu/o3-mini": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/eu/o3-mini-2025-01-31": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
@ -11540,6 +11616,26 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
"cache_read_input_token_cost": 1.375e-06,
"input_cost_per_token": 2.75e-06,
"input_cost_per_token_batches": 1.375e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.1e-05,
"output_cost_per_token_batches": 5.5e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-2024-11-20": {
"deprecation_date": "2027-04-14",
"cache_creation_input_token_cost": 1.38e-06,
@ -11560,6 +11656,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-mini": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
"input_cost_per_token": 1.65e-07,
"input_cost_per_token_batches": 8.3e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6.6e-07,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/gpt-4o-mini-2024-07-18": {
"cache_read_input_token_cost": 8.3e-08,
"deprecation_date": "2027-04-14",
@ -11871,6 +11986,25 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o1": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.65e-05,
"input_cost_per_token_batches": 8.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"output_cost_per_token_batches": 3.3e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o1-2024-12-17": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2026-11-19",
@ -11907,6 +12041,39 @@
"supports_prompt_caching": true,
"supports_vision": false
},
"azure/us/o3": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_batches": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8.8e-06,
"output_cost_per_token_batches": 4.4e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o3-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
@ -11940,6 +12107,24 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o3-mini": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us/o3-mini-2025-01-31": {
"cache_read_input_token_cost": 6.05e-07,
"deprecation_date": "2026-11-19",
@ -11958,6 +12143,27 @@
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us/o4-mini": {
"cache_read_input_token_cost": 3.03e-07,
"deprecation_date": "2026-11-19",
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us/o4-mini-2025-04-16": {
"cache_read_input_token_cost": 3.03e-07,
"deprecation_date": "2026-11-19",
@ -61148,6 +61354,41 @@
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-pro-260915": {
"cache_read_input_token_cost": 1.725e-07,
"input_cost_per_token": 8.625e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 1024000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4.3125e-06,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-lite-260915": {
"cache_read_input_audio_token_cost": 3.45e-07,
"cache_read_input_token_cost": 2.3e-08,
"input_cost_per_audio_token": 1.725e-06,
"input_cost_per_token": 1.15e-07,
"litellm_provider": "volcengine",
"max_input_tokens": 1024000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 3.88126e-07,
"source": "https://www.volcengine.com/docs/82379/1544106",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": false,
"supports_vision": true
},
"volcengine/doubao-seed-2-1-turbo-260628": {
"cache_read_input_token_cost": 8.625e-08,
"input_cost_per_token": 4.3125e-07,
@ -70141,6 +70382,20 @@
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o3": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 2.2e-06,
"input_cost_per_token_batches": 1.1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8.8e-06,
"output_cost_per_token_batches": 4.4e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o3-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
@ -70164,6 +70419,20 @@
"output_cost_per_token": 4.4e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o4-mini": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 3.03e-07,
"input_cost_per_token": 1.21e-06,
"input_cost_per_token_batches": 6.05e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.84e-06,
"output_cost_per_token_batches": 2.42e-06,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'"
},
"azure/eu/o4-mini-2025-04-16": {
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 3.03e-07,

34
tests/unit/test_cost_calculator.py
View file

@ -357,6 +357,40 @@ def test_completion_cost_prices_rule_only_response_model_at_the_azure_deployment
assert cost == pytest.approx(usage.prompt_tokens * 0.0000111 + usage.completion_tokens * 0.0000222)
@pytest.mark.parametrize("region", ["eu", "us"])
@pytest.mark.parametrize(
("alias", "dated"),
[
("o1", "o1-2024-12-17"),
("o3", "o3-2025-04-16"),
("o3-mini", "o3-mini-2025-01-31"),
("o4-mini", "o4-mini-2025-04-16"),
("gpt-4o", "gpt-4o-2024-11-20"),
("gpt-4o-mini", "gpt-4o-mini-2024-07-18"),
],
)
def test_completion_cost_bills_undated_azure_data_zone_base_model_at_its_dated_rate(
_local_model_cost_map: None, region: str, alias: str, dated: str
) -> None:
"""LIT-9812: a deployment with base_model azure/eu/o3 (undated, like the global azure/o3) must bill the EU
Data Zone rate of its latest dated row, not $0 and not the global rate"""
dated_info: Final = litellm.model_cost[f"azure/{region}/{dated}"]
usage: Final = Usage(prompt_tokens=17, completion_tokens=9, total_tokens=26)
response: Final = ModelResponse(model=dated, choices=[], usage=usage)
cost: Final = completion_cost(
completion_response=response,
model="azure/my-data-zone-deployment",
custom_llm_provider="azure",
base_model=f"azure/{region}/{alias}",
)
assert cost == pytest.approx(
usage.prompt_tokens * dated_info["input_cost_per_token"]
+ usage.completion_tokens * dated_info["output_cost_per_token"]
)
def test_completion_cost_orders_candidates_without_extra_huggingface_config_requests(
_local_model_cost_map: None,
) -> None:

23
tests/unit/test_model_prices_and_context_window.py
View file

@ -719,3 +719,26 @@ def test_unregistered_provider_guard_flags_only_labels_nobody_registered():
"unknown_root-new_family_models",
"vertex_ai-new_family_models",
]
@pytest.mark.parametrize("path", (PRICES_PATH, BACKUP_PRICES_PATH), ids=("main", "backup"))
def test_volcengine_doubao_seed_2_1_pro_260915_row_matches_published_metadata(path: Path):
"""Volcengine Ark lists doubao-seed-2-1-pro-260915 at 6 / 30 CNY per million input / output tokens with
cache hits at 1.2 (ark.volcengine.com model detail and docs.volcengine.com/docs/82379/1544106, read
2026-10-20), a 1024k context window and a 256k output cap. USD rows use the 6.9565 CNY/USD rate of the
sibling 260628 row."""
rows: Mapping[str, object] = json.loads(path.read_text())
entry = rows.get("volcengine/doubao-seed-2-1-pro-260915")
assert isinstance(entry, dict)
assert entry["litellm_provider"] == "volcengine"
assert entry["mode"] == "chat"
assert entry["max_input_tokens"] == 1024000
assert entry["max_output_tokens"] == 256000
assert entry["max_tokens"] == 256000
# Volcengine Ark pricing https://www.volcengine.com/docs/82379/1544106 checked 2026-10-20
assert entry["input_cost_per_token"] == pytest.approx(6.0 / 6.9565 / 1_000_000, rel=1e-4)
assert entry["output_cost_per_token"] == pytest.approx(30.0 / 6.9565 / 1_000_000, rel=1e-4)
assert entry["cache_read_input_token_cost"] == pytest.approx(1.2 / 6.9565 / 1_000_000, rel=1e-4)
sibling = rows["volcengine/doubao-seed-2-1-pro-260628"]
assert isinstance(sibling, dict)
assert all(entry[key] == sibling[key] for key in ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost"))