scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-17 04:34:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 171

fix: correct context window for watsonx/ibm/granite-4-h-small

Browse source 
max_tokens, max_input_tokens and max_output_tokens were all 20480, but IBM's
watsonx docs list a 131072-token context window for granite-4-h-small. Update
all three to 131072 (matching the file's convention for the other watsonx
granite entries, which set input == output == context window).

Updated both model_prices_and_context_window.json and the backup copy so they
stay in sync.

Fixes #31954
This commit is contained in:
Carson Rodrigues 2026-07-02 18:20:40 +05:30
parent b96f1aa686
commit 488bc6b860
2 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
litellm/model_prices_and_context_window_backup.json
View file

@ -36887,9 +36887,9 @@
"supports_vision": false
},
"watsonx/ibm/granite-4-h-small": {
"max_tokens": 20480,
"max_input_tokens": 20480,
"max_output_tokens": 20480,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 6e-08,
"output_cost_per_token": 2.5e-07,
"litellm_provider": "watsonx",

6
model_prices_and_context_window.json
View file

@ -37089,9 +37089,9 @@
"supports_vision": false
},
"watsonx/ibm/granite-4-h-small": {
"max_tokens": 20480,
"max_input_tokens": 20480,
"max_output_tokens": 20480,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 6e-08,
"output_cost_per_token": 2.5e-07,
"litellm_provider": "watsonx",