scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-10 08:28:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974)

Browse source 
* chore(cost-map): remove the 52 rows whose provider retired them before 2026

* test(utils): pin the proxy function-calling parity case to azure/gpt-4.1

* test(batches): price the Azure batch-logging regression case against gpt-4.1

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Kerry Lu 2026-11-03 16:23:06 -08:00 • committed by GitHub
parent e9a6a25fe3
commit ce73cf8b9d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
16 changed files with 17 additions and 1482 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
litellm/__init__.py
View file

@ -1074,7 +1074,6 @@ _populate_provider_model_sets(model_cost)
# Azure returns gpt-35-turbo in their responses, we need to map this to azure/gpt-3.5-turbo for token counting
azure_llms = {
"gpt-35-turbo": "azure/gpt-35-turbo",
"gpt-35-turbo-16k": "azure/gpt-35-turbo-16k",
"gpt-35-turbo-instruct": "azure/gpt-35-turbo-instruct",
"azure/gpt-41": "gpt-4.1",
"azure/gpt-41-mini": "gpt-4.1-mini",

6
litellm/llms/azure_ai/rerank/transformation.py
View file

@ -111,10 +111,4 @@ class AzureAIRerankConfig(CohereRerankConfig):
return rerank_response
def _get_base_model(self, azure_model_group: str | None) -> str | None:
if azure_model_group is None:
return None
if azure_model_group == "offer-cohere-rerank-mul-paygo":
return "azure_ai/cohere-rerank-v3-multilingual"
if azure_model_group == "offer-cohere-rerank-eng-paygo":
return "azure_ai/cohere-rerank-v3-english"
return azure_model_group

726
litellm/model_prices_and_context_window_backup.json
View file

@ -3837,18 +3837,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/command-r-plus": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true
},
"azure_ai/claude-haiku-4-5": {
"deprecation_date": "2026-11-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -5282,28 +5270,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/eu/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2.2e-05,
"cache_read_input_token_cost": 2.75e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.00011,
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.00022,
"output_cost_per_token": 2.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/eu/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_audio_token_cost": 2.5e-06,
"cache_read_input_token_cost": 2.75e-06,
@ -5914,30 +5880,6 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k": {
"deprecation_date": "2025-04-30",
"successor_model": "azure/gpt-4.1-mini",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k-0613": {
"deprecation_date": "2025-04-30",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-35-turbo-instruct": {
"input_cost_per_token": 1.65e-06,
"litellm_provider": "azure_text",
@ -5956,20 +5898,6 @@
"output_cost_per_token": 2.2e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
},
"azure/gpt-4": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-0125-preview": {
"input_cost_per_token": 1e-05,
"litellm_provider": "azure",
@ -5981,20 +5909,6 @@
"supports_parallel_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-1106-preview": {
"input_cost_per_token": 1e-05,
"litellm_provider": "azure",
@ -6006,30 +5920,6 @@
"supports_parallel_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-32k": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00012,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-4-32k-0613": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00012,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-4-turbo": {
"input_cost_per_token": 1.1e-05,
"litellm_provider": "azure",
@ -6312,28 +6202,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/gpt-4.5-preview": {
"cache_read_input_token_cost": 3.75e-05,
"deprecation_date": "2025-07-14",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 7.5e-05,
"input_cost_per_token_batches": 3.75e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.00015,
"output_cost_per_token_batches": 7.5e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/gpt-4o": {
"deprecation_date": "2027-04-14",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
@ -7092,28 +6960,6 @@
"audio"
]
},
"azure/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2e-05,
"cache_read_input_token_cost": 2.5e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.0001,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.0002,
"output_cost_per_token": 2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_token_cost": 2.5e-06,
"input_cost_per_audio_token": 4e-05,
@ -7930,40 +7776,6 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"azure/us/o1-preview": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2025-07-28",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/us/o1",
"input_cost_per_token": 1.65e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_prompt_caching": true
},
"azure/eu/o1-preview": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2025-07-28",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/eu/o1",
"input_cost_per_token": 1.65e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_prompt_caching": true
},
"azure/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
@ -12494,28 +12306,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2.2e-05,
"cache_read_input_token_cost": 2.75e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.00011,
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.00022,
"output_cost_per_token": 2.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_audio_token_cost": 2.5e-06,
"cache_read_input_token_cost": 2.75e-06,
@ -13538,169 +13328,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/Meta-Llama-3-70B-Instruct": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Llama-3.3-70B-Instruct",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.7e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Llama-3.3-70B-Instruct",
"input_cost_per_token": 2.68e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.54e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/Phi-3-medium-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4",
"input_cost_per_token": 1.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.8e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-medium-4k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4",
"input_cost_per_token": 1.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.8e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-mini-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-mini-4k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-small-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-small-8k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-MoE-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.4e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-mini-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-vision-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/Phi-4": {
"deprecation_date": "2027-01-17",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -13864,32 +13491,6 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/cohere-rerank-v3-english": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/cohere-rerank-v4.0-pro",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
},
"azure_ai/cohere-rerank-v3-multilingual": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/cohere-rerank-v4.0-pro",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
},
"azure_ai/cohere-rerank-v4.0-pro": {
"deprecation_date": "2027-09-13",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -13952,20 +13553,6 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v3": {
"deprecation_date": "2025-08-31",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/deepseek-v3-0324",
"input_cost_per_token": 1.14e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"deprecation_date": "2028-02-20",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -14202,19 +13789,6 @@
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false
},
"azure_ai/jamba-instruct": {
"deprecation_date": "2025-03-01",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"input_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 70000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"deprecation_date": "2027-01-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -14273,36 +13847,6 @@
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large": {
"deprecation_date": "2025-04-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-medium-2505",
"input_cost_per_token": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large-2407": {
"deprecation_date": "2025-05-13",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-medium-2505",
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large-latest": {
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
@ -14357,21 +13901,6 @@
"supports_function_calling": true,
"supports_pdf_input": false
},
"azure_ai/mistral-small": {
"deprecation_date": "2025-07-31",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-small-2503",
"input_cost_per_token": 1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-small-2503": {
"deprecation_date": "2027-02-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -16696,17 +16225,6 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"cerebras/llama3.1-70b": {
"deprecation_date": "2025-01-17",
"input_cost_per_token": 6e-07,
"litellm_provider": "cerebras",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_tool_choice": true
},
"cerebras/llama3.1-8b": {
"deprecation_date": "2026-05-27",
"input_cost_per_token": 1e-07,
@ -40657,17 +40175,6 @@
"supports_response_schema": true,
"supports_vision": true
},
"groq/llama-guard-3-8b": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://console.groq.com/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://console.groq.com/docs/model/llama-guard-3-8b"
},
"groq/meta-llama/llama-prompt-guard-2-22m": {
"input_cost_per_token": 3e-08,
"litellm_provider": "groq",
@ -52876,32 +52383,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-opus": {
"deprecation_date": "2025-08-01",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7.5e-05,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-opus@20240229": {
"deprecation_date": "2025-08-01",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7.5e-05,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-sonnet": {
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
@ -60251,48 +59732,6 @@
"/v1/images/edits"
]
},
"gemini-2.0-flash-exp-image-generation": {
"deprecation_date": "2025-11-14",
"input_cost_per_token": 0.0,
"litellm_provider": "gemini",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.039,
"output_cost_per_token": 0.0,
"source": "https://ai.google.dev/pricing",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_vision": true
},
"gemini/gemini-2.0-flash-exp-image-generation": {
"deprecation_date": "2025-11-14",
"input_cost_per_token": 0.0,
"litellm_provider": "gemini",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.039,
"output_cost_per_token": 0.0,
"source": "https://ai.google.dev/pricing",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_vision": true,
"tpm": 250000,
"rpm": 10
},
"gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
@ -71433,50 +70872,6 @@
"output_cost_per_token": 0.0,
"source": "https://api.together.ai/v1/models"
},
"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/QwQ-32B": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2-72B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 9e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 9e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2-VL-72B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": {
"deprecation_date": "2026-02-06",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71488,17 +70883,6 @@
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-VL-72B-Instruct": {
"deprecation_date": "2026-01-05",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71588,39 +70972,6 @@
"output_cost_per_token": 3.6e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
"deprecation_date": "2025-12-23",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.6e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.6e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-V3.1": {
"deprecation_date": "2026-05-14",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71632,28 +70983,6 @@
"output_cost_per_token": 1.7e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/deepseek-coder-33b-instruct": {
"deprecation_date": "2024-08-22",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/google/gemma-2-27b-it": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/google/gemma-4-31B-it": {
"deprecation_date": "2026-09-15",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71665,17 +70994,6 @@
"output_cost_per_token": 9.7e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Llama-3-8b-chat-hf": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"deprecation_date": "2026-02-06",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71687,28 +71005,6 @@
"output_cost_per_token": 5.9e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
"deprecation_date": "2025-12-23",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 8.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3-8B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"deprecation_date": "2026-02-25",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71731,17 +71027,6 @@
"output_cost_per_token": 1.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.1": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
"deprecation_date": "2026-04-02",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71788,17 +71073,6 @@
"output_cost_per_token": 4e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
"cache_read_input_token_cost": 2e-07,
"deprecation_date": "2026-08-27",

726
model_prices_and_context_window.json
View file

@ -3837,18 +3837,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/command-r-plus": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true
},
"azure_ai/claude-haiku-4-5": {
"deprecation_date": "2026-11-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -5282,28 +5270,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/eu/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2.2e-05,
"cache_read_input_token_cost": 2.75e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.00011,
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.00022,
"output_cost_per_token": 2.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/eu/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_audio_token_cost": 2.5e-06,
"cache_read_input_token_cost": 2.75e-06,
@ -5914,30 +5880,6 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k": {
"deprecation_date": "2025-04-30",
"successor_model": "azure/gpt-4.1-mini",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k-0613": {
"deprecation_date": "2025-04-30",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-35-turbo-instruct": {
"input_cost_per_token": 1.65e-06,
"litellm_provider": "azure_text",
@ -5956,20 +5898,6 @@
"output_cost_per_token": 2.2e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/"
},
"azure/gpt-4": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-0125-preview": {
"input_cost_per_token": 1e-05,
"litellm_provider": "azure",
@ -5981,20 +5909,6 @@
"supports_parallel_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-1106-preview": {
"input_cost_per_token": 1e-05,
"litellm_provider": "azure",
@ -6006,30 +5920,6 @@
"supports_parallel_function_calling": true,
"supports_tool_choice": true
},
"azure/gpt-4-32k": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00012,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-4-32k-0613": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00012,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_tool_choice": true
},
"azure/gpt-4-turbo": {
"input_cost_per_token": 1.1e-05,
"litellm_provider": "azure",
@ -6312,28 +6202,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure/gpt-4.5-preview": {
"cache_read_input_token_cost": 3.75e-05,
"deprecation_date": "2025-07-14",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"successor_model": "azure/gpt-4.1",
"input_cost_per_token": 7.5e-05,
"input_cost_per_token_batches": 3.75e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.00015,
"output_cost_per_token_batches": 7.5e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/gpt-4o": {
"deprecation_date": "2027-04-14",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
@ -7092,28 +6960,6 @@
"audio"
]
},
"azure/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2e-05,
"cache_read_input_token_cost": 2.5e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.0001,
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.0002,
"output_cost_per_token": 2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_token_cost": 2.5e-06,
"input_cost_per_audio_token": 4e-05,
@ -7930,40 +7776,6 @@
"supports_response_schema": true,
"supports_tool_choice": true
},
"azure/us/o1-preview": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2025-07-28",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/us/o1",
"input_cost_per_token": 1.65e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_prompt_caching": true
},
"azure/eu/o1-preview": {
"cache_read_input_token_cost": 8.25e-06,
"deprecation_date": "2025-07-28",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure/eu/o1",
"input_cost_per_token": 1.65e-05,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6.6e-05,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_prompt_caching": true
},
"azure/gpt-5.1-codex": {
"deprecation_date": "2027-05-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
@ -12494,28 +12306,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-realtime-preview-2024-10-01": {
"cache_creation_input_audio_token_cost": 2.2e-05,
"cache_read_input_token_cost": 2.75e-06,
"deprecation_date": "2025-03-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "gpt-4o-realtime-preview",
"input_cost_per_audio_token": 0.00011,
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "realtime",
"output_cost_per_audio_token": 0.00022,
"output_cost_per_token": 2.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-realtime-preview-2024-12-17": {
"cache_read_input_audio_token_cost": 2.5e-06,
"cache_read_input_token_cost": 2.75e-06,
@ -13538,169 +13328,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/Meta-Llama-3-70B-Instruct": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Llama-3.3-70B-Instruct",
"input_cost_per_token": 1.1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 8192,
"max_output_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.7e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Llama-3.3-70B-Instruct",
"input_cost_per_token": 2.68e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 3.54e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/Phi-3-medium-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4",
"input_cost_per_token": 1.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.8e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-medium-4k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4",
"input_cost_per_token": 1.7e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.8e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-mini-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-mini-4k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-small-128k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3-small-8k-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-MoE-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.6e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6.4e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-mini-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": false
},
"azure_ai/Phi-3.5-vision-instruct": {
"deprecation_date": "2025-08-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/Phi-4-mini-instruct",
"input_cost_per_token": 1.3e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 5.2e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true,
"supports_vision": true
},
"azure_ai/Phi-4": {
"deprecation_date": "2027-01-17",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -13864,32 +13491,6 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/cohere-rerank-v3-english": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/cohere-rerank-v4.0-pro",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
},
"azure_ai/cohere-rerank-v3-multilingual": {
"deprecation_date": "2025-06-30",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/cohere-rerank-v4.0-pro",
"input_cost_per_query": 0.002,
"input_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "rerank",
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models"
},
"azure_ai/cohere-rerank-v4.0-pro": {
"deprecation_date": "2027-09-13",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -13952,20 +13553,6 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/deepseek-v3": {
"deprecation_date": "2025-08-31",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/deepseek-v3-0324",
"input_cost_per_token": 1.14e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 4.56e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/deepseek-v4-pro": {
"deprecation_date": "2028-02-20",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -14202,19 +13789,6 @@
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false
},
"azure_ai/jamba-instruct": {
"deprecation_date": "2025-03-01",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"input_cost_per_token": 5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 70000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7e-07,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/kimi-k2.5": {
"deprecation_date": "2027-01-26",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -14273,36 +13847,6 @@
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large": {
"deprecation_date": "2025-04-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-medium-2505",
"input_cost_per_token": 4e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large-2407": {
"deprecation_date": "2025-05-13",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-medium-2505",
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 6e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-large-latest": {
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
@ -14357,21 +13901,6 @@
"supports_function_calling": true,
"supports_pdf_input": false
},
"azure_ai/mistral-small": {
"deprecation_date": "2025-07-31",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"successor_model": "azure_ai/mistral-small-2503",
"input_cost_per_token": 1e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models",
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_tool_choice": true
},
"azure_ai/mistral-small-2503": {
"deprecation_date": "2027-02-15",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
@ -16696,17 +16225,6 @@
"supports_function_calling": true,
"supports_tool_choice": true
},
"cerebras/llama3.1-70b": {
"deprecation_date": "2025-01-17",
"input_cost_per_token": 6e-07,
"litellm_provider": "cerebras",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_tool_choice": true
},
"cerebras/llama3.1-8b": {
"deprecation_date": "2026-05-27",
"input_cost_per_token": 1e-07,
@ -40657,17 +40175,6 @@
"supports_response_schema": true,
"supports_vision": true
},
"groq/llama-guard-3-8b": {
"deprecation_date": "2025-06-06",
"deprecation_source": "https://console.groq.com/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "groq",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://console.groq.com/docs/model/llama-guard-3-8b"
},
"groq/meta-llama/llama-prompt-guard-2-22m": {
"input_cost_per_token": 3e-08,
"litellm_provider": "groq",
@ -52876,32 +52383,6 @@
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-opus": {
"deprecation_date": "2025-08-01",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7.5e-05,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-opus@20240229": {
"deprecation_date": "2025-08-01",
"input_cost_per_token": 1.5e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 7.5e-05,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true
},
"vertex_ai/claude-3-sonnet": {
"input_cost_per_token": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
@ -60251,48 +59732,6 @@
"/v1/images/edits"
]
},
"gemini-2.0-flash-exp-image-generation": {
"deprecation_date": "2025-11-14",
"input_cost_per_token": 0.0,
"litellm_provider": "gemini",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.039,
"output_cost_per_token": 0.0,
"source": "https://ai.google.dev/pricing",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_vision": true
},
"gemini/gemini-2.0-flash-exp-image-generation": {
"deprecation_date": "2025-11-14",
"input_cost_per_token": 0.0,
"litellm_provider": "gemini",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.039,
"output_cost_per_token": 0.0,
"source": "https://ai.google.dev/pricing",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_vision": true,
"tpm": 250000,
"rpm": 10
},
"gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
@ -71433,50 +70872,6 @@
"output_cost_per_token": 0.0,
"source": "https://api.together.ai/v1/models"
},
"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 6e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 6e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/QwQ-32B": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2-72B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 9e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 9e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2-VL-72B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": {
"deprecation_date": "2026-02-06",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71488,17 +70883,6 @@
"output_cost_per_token": 1.2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/Qwen/Qwen2.5-VL-72B-Instruct": {
"deprecation_date": "2026-01-05",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71588,39 +70972,6 @@
"output_cost_per_token": 3.6e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
"deprecation_date": "2025-12-23",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 1.6e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 1.6e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/DeepSeek-V3.1": {
"deprecation_date": "2026-05-14",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71632,28 +70983,6 @@
"output_cost_per_token": 1.7e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/deepseek-ai/deepseek-coder-33b-instruct": {
"deprecation_date": "2024-08-22",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/google/gemma-2-27b-it": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/google/gemma-4-31B-it": {
"deprecation_date": "2026-09-15",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71665,17 +70994,6 @@
"output_cost_per_token": 9.7e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Llama-3-8b-chat-hf": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
"deprecation_date": "2026-02-06",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71687,28 +71005,6 @@
"output_cost_per_token": 5.9e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
"deprecation_date": "2025-12-23",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 8.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3-8B-Instruct": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
"deprecation_date": "2026-02-25",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71731,17 +71027,6 @@
"output_cost_per_token": 1.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.1": {
"deprecation_date": "2025-11-13",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 2e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
"deprecation_date": "2026-04-02",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
@ -71788,17 +71073,6 @@
"output_cost_per_token": 4e-06,
"source": "https://api.together.ai/v1/models"
},
"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
"deprecation_date": "2025-08-28",
"deprecation_source": "https://docs.together.ai/docs/deprecations",
"input_cost_per_token": 8.8e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8.8e-07,
"source": "https://api.together.ai/v1/models"
},
"together_ai/nvidia/nemotron-3-ultra-550b-a55b": {
"cache_read_input_token_cost": 2e-07,
"deprecation_date": "2026-08-27",

2
tests/integration/providers/test_responses_minted_reasoning_replay_chaos.py
View file

@ -419,7 +419,7 @@ class _LoginDeployment:
_LOGIN_DEPLOYMENTS: Final = (
_LoginDeployment("github_copilot", f"github_copilot/{_CODEX}", None),
_LoginDeployment("chatgpt", f"chatgpt/{_CODEX}", None),
_LoginDeployment("azure_ai-foundry-host", "azure_ai/deepseek-v3", "synthetic-azure-key"),
_LoginDeployment("azure_ai-foundry-host", "azure_ai/deepseek-v3.2", "synthetic-azure-key"),
)

2
tests/unit/batches/test_main.py
View file

@ -858,7 +858,7 @@ async def test_batch_logging_azure_credentials_regression():
"timeout": 600,
}
batch_output = b'{"id": "batch_req_1", "custom_id": "request-1", "response": {"status_code": 200, "body": {"id": "chatcmpl-azure", "object": "chat.completion", "model": "gpt-4", "usage": {"prompt_tokens": 15, "completion_tokens": 25, "total_tokens": 40}}}}\n'
batch_output = b'{"id": "batch_req_1", "custom_id": "request-1", "response": {"status_code": 200, "body": {"id": "chatcmpl-azure", "object": "chat.completion", "model": "gpt-4.1", "usage": {"prompt_tokens": 15, "completion_tokens": 25, "total_tokens": 40}}}}\n'
print("\n1. Testing credential extraction...")

5
tests/unit/litellm_core_utils/test_token_counter.py
View file

@ -1246,7 +1246,7 @@ def test_token_counter_counts_deepseek_v3_and_v4_with_the_packaged_deepseek_toke
@pytest.mark.parametrize(
"model",
["together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "fireworks_ai/accounts/fireworks/models/deepseek-v2p5"],
["deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "fireworks_ai/accounts/fireworks/models/deepseek-v2p5"],
)
def test_token_counter_skips_the_deepseek_tokenizer_for_deepseek_models_built_on_other_vocabularies(model: str):
assert litellm.token_counter(model=model, text=_CODE_SAMPLE) != _deepseek_token_count(_CODE_SAMPLE)
@ -2875,7 +2875,7 @@ def test_prefixed_openai_model_names_count_text_like_the_model_they_name(deploym
@pytest.mark.parametrize(
"model", ["azure/gpt-chat-latest", "azure/codex-mini", "azure/gpt-5.3-chat", "azure/gpt-4.5-preview"]
"model", ["azure/gpt-chat-latest", "azure/codex-mini", "azure/gpt-5.3-chat"]
)
def test_azure_openai_models_only_azure_lists_get_openai_pricing_and_o200k(model: str):
assert _pdf_cost(model, _pdf_base64((_REVENUE_LINE,))) == _text_cost(model, _REVENUE_LINE) + 13
@ -3594,7 +3594,6 @@ def test_token_counter_counts_unlisted_names_of_newer_openai_releases_with_o200k
"azure/my-deployment",
"azure/ada",
"azure/mistral-large-latest",
"azure/command-r-plus",
"azure_ai/mistral-large-latest",
],
)

4
tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py
View file

@ -1360,7 +1360,7 @@ def test_azure_ai_services_handler(api_base, expected_url):
with patch.object(client, "post") as mock_client:
try:
response = litellm.completion(
model="azure_ai/Meta-Llama-3.1-70B-Instruct",
model="azure_ai/Llama-3.3-70B-Instruct",
messages=[{"role": "user", "content": "Hello, how are you?"}],
api_key="my-fake-api-key",
api_base=api_base,
@ -1385,7 +1385,7 @@ def test_azure_ai_services_with_api_version():
with patch.object(client, "post") as mock_client:
try:
response = litellm.completion(
model="azure_ai/Meta-Llama-3.1-70B-Instruct",
model="azure_ai/Llama-3.3-70B-Instruct",
messages=[{"role": "user", "content": "Hello, how are you?"}],
api_key="my-fake-api-key",
api_version="2024-05-01-preview",

6
tests/unit/llms/azure_ai/rerank/test_azure_ai_rerank_transformation.py
View file

@ -9,7 +9,7 @@ from litellm.llms.azure_ai.rerank.transformation import AzureAIRerankConfig
class TestAzureAIRerankConfigGetCompleteUrl:
def setup_method(self):
self.config = AzureAIRerankConfig()
self.model = "azure_ai/cohere-rerank-v3-english"
self.model = "azure_ai/cohere-rerank-v4.0-pro"
def test_api_base_required(self):
with pytest.raises(ValueError, match='Azure AI API Base is required\\. api_base=None\\. Set in') as exc_info:
@ -99,7 +99,7 @@ class TestAzureAIRerankConfigValidateEnvironment:
def test_uses_api_key_when_set(self):
headers = AzureAIRerankConfig().validate_environment(
headers={},
model="azure_ai/cohere-rerank-v3-english",
model="azure_ai/cohere-rerank-v4.0-pro",
api_key="my-key",
)
@ -111,7 +111,7 @@ class TestAzureAIRerankConfigValidateEnvironment:
headers = AzureAIRerankConfig().validate_environment(
headers={},
model="azure_ai/cohere-rerank-v3-english",
model="azure_ai/cohere-rerank-v4.0-pro",
litellm_params={"azure_ad_token": "entra-token"},
)

2
tests/unit/llms/gemini/test_gemini_client_setup.py
View file

@ -12,7 +12,7 @@ def mock_gemini_api_key(monkeypatch):
def test_gemini_completion():
response = completion(
model="gemini/gemini-2.0-flash-exp-image-generation",
model="gemini/gemini-2.5-flash",
messages=[{"role": "user", "content": "Test message"}],
mock_response="Test Message",
)

1
tests/unit/test_cerebras_llama_model_metadata.py
View file

@ -52,7 +52,6 @@ CEREBRAS_MODELS_EXPECTED = {
PAIR_PARITY = [
("cerebras/llama-3.1-8b", "cerebras/llama3.1-8b"),
("cerebras/llama-3.1-70b", "cerebras/llama3.1-70b"),
]

8
tests/unit/test_cost_calculator.py
View file

@ -8318,7 +8318,7 @@ def test_cost_openai_prompt_caching():
"model",
[
"cohere/rerank-english-v3.0",
"azure_ai/cohere-rerank-v3-english",
"azure_ai/cohere-rerank-v4.0-pro",
],
)
def test_completion_cost_azure_ai_rerank(model):
@ -9371,7 +9371,7 @@ async def test_test_completion_cost_gpt4o_audio_output_from_model(stream):
@pytest.mark.parametrize(
"response_model, custom_llm_provider",
[
("azure_ai/Meta-Llama-3.1-70B-Instruct", "azure_ai"),
("azure_ai/Llama-3.3-70B-Instruct", "azure_ai"),
("anthropic.claude-3-5-sonnet-20240620-v1:0", "bedrock"),
],
)
@ -9431,7 +9431,7 @@ def test_select_model_name_for_cost_calc():
"completion_response": ModelResponse(
id="127f24aed4984b4c9a4c5e32ad3752f3",
created=1734406048,
model="azure_ai/mistral-large",
model="azure_ai/mistral-large-latest",
object="chat.completion",
system_fingerprint=None,
choices=[
@ -9460,7 +9460,7 @@ def test_select_model_name_for_cost_calc():
}
return_model = select_model_name_for_cost_calc(**args)
assert return_model == "azure_ai/mistral-large"
assert return_model == "azure_ai/mistral-large-latest"
def test_cost_calculator_with_base_model():

2
tests/unit/test_count_tokens_public_api.py
View file

@ -59,7 +59,7 @@ def test_acount_tokens_fallback_to_local():
"""Test that unsupported providers fall back to local tiktoken counting."""
result = asyncio.run(
litellm.acount_tokens(
model="together_ai/meta-llama/Llama-3-8b-chat-hf",
model="together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo",
messages=[{"role": "user", "content": "Hello"}],
)
)

3
tests/unit/test_gpt_realtime_mode.py
View file

@ -24,13 +24,10 @@ REALTIME_ONLY_GPT_MODELS = (
REALTIME_ONLY_GPT_MODELS_WITHOUT_ENDPOINTS = (
"azure/eu/gpt-4o-mini-realtime-preview-2024-12-17",
"azure/eu/gpt-4o-realtime-preview-2024-10-01",
"azure/eu/gpt-4o-realtime-preview-2024-12-17",
"azure/gpt-4o-mini-realtime-preview-2024-12-17",
"azure/gpt-4o-realtime-preview-2024-10-01",
"azure/gpt-4o-realtime-preview-2024-12-17",
"azure/us/gpt-4o-mini-realtime-preview-2024-12-17",
"azure/us/gpt-4o-realtime-preview-2024-10-01",
"azure/us/gpt-4o-realtime-preview-2024-12-17",
"gpt-4o-mini-realtime-preview",
"gpt-4o-mini-realtime-preview-2024-12-17",

1
tests/unit/test_together_ai_model_metadata.py
View file

@ -64,7 +64,6 @@ DEPRECATED_MODELS: Final = {
"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": "2026-02-06",
"together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": "2026-02-06",
"together_ai/deepseek-ai/DeepSeek-R1-0528-tput": "2026-02-03",
"together_ai/mistralai/Mistral-7B-Instruct-v0.1": "2025-11-13",
"together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": "2025-11-13",
}

4
tests/unit/test_utils.py
View file

@ -1911,7 +1911,7 @@ class TestProxyFunctionCalling:
("gpt-4-turbo", "litellm_proxy/gpt-4-turbo", True),
("gpt-4-1106-preview", "litellm_proxy/gpt-4-1106-preview", True),
# Azure OpenAI models
("azure/gpt-4", "litellm_proxy/azure/gpt-4", True),
("azure/gpt-4.1", "litellm_proxy/azure/gpt-4.1", True),
("azure/gpt-3.5-turbo", "litellm_proxy/azure/gpt-3.5-turbo", True),
(
"azure/gpt-4-1106-preview",
@ -2004,7 +2004,7 @@ class TestProxyFunctionCalling:
),
(
"litellm_proxy/together-mistral",
"together_ai/mistralai/Mistral-7B-Instruct-v0.1",
"together_ai/mistralai/Mistral-7B-Instruct-v0.3",
False,
),
# Ollama with custom names (cannot be resolved)