scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-01 07:03:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 129

fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)

Browse source 
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-10-29 21:04:22 -07:00 • committed by GitHub
parent b91fc92b6d
commit ccc56d27ad
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 30 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
litellm/model_prices_and_context_window_backup.json
View file

@ -6014,11 +6014,14 @@
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_batches": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -6313,16 +6316,19 @@
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 7.5e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -11303,16 +11309,19 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"output_cost_per_token_batches": 4e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -11411,11 +11420,14 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_batches": 5.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"output_cost_per_token_batches": 2.2e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -11513,16 +11525,19 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_batches": 5.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"output_cost_per_token_batches": 2.2e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",

15
model_prices_and_context_window.json
View file

@ -6014,11 +6014,14 @@
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_batches": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"output_cost_per_token_batches": 5e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -6313,16 +6316,19 @@
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 1.5e-07,
"input_cost_per_token_batches": 7.5e-08,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6e-07,
"output_cost_per_token_batches": 3e-07,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
@ -11303,16 +11309,19 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"output_cost_per_token_batches": 4e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@ -11411,11 +11420,14 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 5.5e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_batches": 5.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"output_cost_per_token_batches": 2.2e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
@ -11513,16 +11525,19 @@
"deprecation_date": "2026-11-19",
"cache_read_input_token_cost": 2.75e-07,
"input_cost_per_token": 1.1e-06,
"input_cost_per_token_batches": 5.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"output_cost_per_token_batches": 2.2e-06,
"search_context_cost_per_query": {
"search_context_size_high": 0.014,
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014
},
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",