scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

fix: correct context window sizes for GPT-5 model variants (#18928)

Browse source 
* fix: correct context window sizes for GPT-5 model variants

Updates max_input_tokens for GPT-5, GPT-5.1, and GPT-5.2 model variants
to match OpenAI's official specifications, resolving issue #18927.

Changes:
- GPT-5.1 (base, codex variants): 272k → 400k tokens
- GPT-5.1-chat variants: 272k → 128k tokens (with max_output 16,384)
- GPT-5 (base): 272k → 400k tokens
- GPT-5-chat: 272k → 128k tokens (with max_output 16,384)
- GPT-5-codex: 272k → 400k tokens
- GPT-5-mini: 272k → 400k tokens
- GPT-5-nano: 272k → 400k tokens
- GPT-5-pro: 272k → 400k tokens (max_output 272k)
- GPT-5 dated versions (2025-08-07): 272k → 400k tokens

Affected providers: OpenAI, Azure (all regions), OpenRouter

Fixes #18927

* fix: correct Azure GPT-5 context window limits to match Azure docs

Azure OpenAI has different limits than OpenAI for GPT-5 models.

Changes:
- Azure GPT-5 models: max_input_tokens 400k → 272k (Azure limit)
- Azure GPT-5 Pro: max_output_tokens 272k → 128k (Azure limit)
- OpenAI GPT-5 models: remain at 400k (correct)
- OpenRouter models: remain at 400k (routes to OpenAI)

Azure docs specify 272k input + 128k output = 400k total context.
OpenAI allows full 400k input + 128k output.

* fix: correct Azure GPT-5 max_input_tokens to 272k

Azure has explicit input limit of 272k tokens (not 400k like OpenAI).
Context window 400k = 272k input + 128k output for Azure.
OpenAI allows flexible input up to 400k (context - output).
This commit is contained in:
Cesar Garcia 2026-01-13 19:19:47 -03:00 • committed by GitHub
parent b7c5662273
commit d03c5017ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 35 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

70
model_prices_and_context_window.json
View file

@ -1644,7 +1644,7 @@
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.38e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1944,7 +1944,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -2893,7 +2893,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -2964,7 +2964,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -2997,7 +2997,7 @@
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -3092,9 +3092,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/",
@ -3377,7 +3377,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -3440,7 +3440,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -3500,7 +3500,7 @@
"cache_read_input_token_cost": 1.75e-07,
"input_cost_per_token": 1.75e-06,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -3637,7 +3637,7 @@
"azure/gpt-5.2-pro": {
"input_cost_per_token": 2.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -3668,7 +3668,7 @@
"azure/gpt-5.2-pro-2025-12-11": {
"input_cost_per_token": 2.1e-05,
"litellm_provider": "azure",
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -4684,7 +4684,7 @@
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.38e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -17470,7 +17470,7 @@
"input_cost_per_token_flex": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -17507,7 +17507,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -17543,7 +17543,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -17852,7 +17852,7 @@
"input_cost_per_token_flex": 6.25e-07,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -17887,9 +17887,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"supported_endpoints": [
@ -17951,7 +17951,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -17983,7 +17983,7 @@
"input_cost_per_token": 1.25e-06,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -18046,7 +18046,7 @@
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
@ -18081,7 +18081,7 @@
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -18120,7 +18120,7 @@
"input_cost_per_token_flex": 1.25e-07,
"input_cost_per_token_priority": 4.5e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -18158,7 +18158,7 @@
"input_cost_per_token_flex": 2.5e-08,
"input_cost_per_token_priority": 2.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -18193,7 +18193,7 @@
"input_cost_per_token": 5e-08,
"input_cost_per_token_flex": 2.5e-08,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23206,9 +23206,9 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1e-05,
"supported_modalities": [
@ -23225,7 +23225,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23244,7 +23244,7 @@
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_token": 1.25e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23263,7 +23263,7 @@
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23282,7 +23282,7 @@
"cache_read_input_token_cost": 5e-09,
"input_cost_per_token": 5e-08,
"litellm_provider": "openrouter",
"max_input_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",