scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 99

chore(cost-map): add azure retirement dates from the retired Foundry models page (#43104)

Browse source 
* chore(cost-map): add azure retirement dates from the retired Foundry models page

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

* fix(cost-map): correct azure/ada retirement date to text-embedding-ada-002 schedule

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

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-24 19:16:45 -07:00 • committed by GitHub
parent 5a75f09d6d
commit 3d5660f32e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 30 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
litellm/model_prices_and_context_window_backup.json
View file

@ -3301,12 +3301,14 @@
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"azure/ada": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1e-07,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
},
"azure/codex-mini": {
"cache_read_input_token_cost": 3.75e-07,
@ -5151,6 +5153,7 @@
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k": {
"deprecation_date": "2025-04-30",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
@ -5158,9 +5161,11 @@
"max_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,
@ -5168,6 +5173,7 @@
"max_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
},
@ -5211,6 +5217,7 @@
"supports_tool_choice": true
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5218,6 +5225,7 @@
"max_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
},
@ -5234,6 +5242,7 @@
"supports_tool_choice": true
},
"azure/gpt-4-32k": {
"deprecation_date": "2025-06-06",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
@ -5241,9 +5250,11 @@
"max_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",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
@ -5251,6 +5262,7 @@
"max_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": {
@ -5511,6 +5523,7 @@
},
"azure/gpt-4.5-preview": {
"cache_read_input_token_cost": 3.75e-05,
"deprecation_date": "2025-07-14",
"input_cost_per_token": 7.5e-05,
"input_cost_per_token_batches": 3.75e-05,
"litellm_provider": "azure",
@ -5520,6 +5533,7 @@
"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,

16
model_prices_and_context_window.json
View file

@ -3301,12 +3301,14 @@
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"azure/ada": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1e-07,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
"output_cost_per_token": 0.0,
"source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule"
},
"azure/codex-mini": {
"cache_read_input_token_cost": 3.75e-07,
@ -5151,6 +5153,7 @@
"supports_tool_choice": true
},
"azure/gpt-35-turbo-16k": {
"deprecation_date": "2025-04-30",
"input_cost_per_token": 3e-06,
"litellm_provider": "azure",
"max_input_tokens": 16385,
@ -5158,9 +5161,11 @@
"max_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,
@ -5168,6 +5173,7 @@
"max_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
},
@ -5211,6 +5217,7 @@
"supports_tool_choice": true
},
"azure/gpt-4-0613": {
"deprecation_date": "2025-06-06",
"input_cost_per_token": 3e-05,
"litellm_provider": "azure",
"max_input_tokens": 8192,
@ -5218,6 +5225,7 @@
"max_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
},
@ -5234,6 +5242,7 @@
"supports_tool_choice": true
},
"azure/gpt-4-32k": {
"deprecation_date": "2025-06-06",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
@ -5241,9 +5250,11 @@
"max_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",
"input_cost_per_token": 6e-05,
"litellm_provider": "azure",
"max_input_tokens": 32768,
@ -5251,6 +5262,7 @@
"max_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": {
@ -5511,6 +5523,7 @@
},
"azure/gpt-4.5-preview": {
"cache_read_input_token_cost": 3.75e-05,
"deprecation_date": "2025-07-14",
"input_cost_per_token": 7.5e-05,
"input_cost_per_token_batches": 3.75e-05,
"litellm_provider": "azure",
@ -5520,6 +5533,7 @@
"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,