scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87

fix(model_prices): set watsonx max_output_tokens from IBM's documented maximum new tokens

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-02 20:38:45 +00:00
parent 671559e591
commit e148868f0c
2 changed files with 24 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
litellm/model_prices_and_context_window_backup.json
View file

@ -46960,9 +46960,9 @@
"supports_vision": false
},
"watsonx/ibm/granite-4-h-small": {
"max_tokens": 20480,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 20480,
"max_output_tokens": 131072,
"input_cost_per_token": 6.36e-08,
"output_cost_per_token": 2.65e-07,
"litellm_provider": "watsonx",
@ -47093,9 +47093,9 @@
"supports_vision": true
},
"watsonx/meta-llama/llama-3-3-70b-instruct": {
"max_tokens": 128000,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 131072,
"input_cost_per_token": 7.526e-07,
"output_cost_per_token": 7.526e-07,
"litellm_provider": "watsonx",
@ -47106,9 +47106,9 @@
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
},
"watsonx/meta-llama/llama-4-maverick-17b": {
"max_tokens": 128000,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 3.71e-07,
"output_cost_per_token": 1.484e-06,
"litellm_provider": "watsonx",
@ -47119,9 +47119,9 @@
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
},
"watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": {
"max_tokens": 128000,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 3.71e-07,
"output_cost_per_token": 1.484e-06,
"litellm_provider": "watsonx",
@ -47168,9 +47168,9 @@
"supports_vision": false
},
"watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": {
"max_tokens": 32000,
"max_tokens": 16384,
"max_input_tokens": 131072,
"max_output_tokens": 32000,
"max_output_tokens": 16384,
"input_cost_per_token": 1.06e-07,
"output_cost_per_token": 3.18e-07,
"litellm_provider": "watsonx",
@ -47193,9 +47193,9 @@
"supports_vision": true
},
"watsonx/openai/gpt-oss-120b": {
"max_tokens": 8192,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_output_tokens": 131072,
"input_cost_per_token": 1.59e-07,
"output_cost_per_token": 6.36e-07,
"litellm_provider": "watsonx",

24
model_prices_and_context_window.json
View file

@ -46960,9 +46960,9 @@
"supports_vision": false
},
"watsonx/ibm/granite-4-h-small": {
"max_tokens": 20480,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 20480,
"max_output_tokens": 131072,
"input_cost_per_token": 6.36e-08,
"output_cost_per_token": 2.65e-07,
"litellm_provider": "watsonx",
@ -47093,9 +47093,9 @@
"supports_vision": true
},
"watsonx/meta-llama/llama-3-3-70b-instruct": {
"max_tokens": 128000,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 131072,
"input_cost_per_token": 7.526e-07,
"output_cost_per_token": 7.526e-07,
"litellm_provider": "watsonx",
@ -47106,9 +47106,9 @@
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
},
"watsonx/meta-llama/llama-4-maverick-17b": {
"max_tokens": 128000,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 3.71e-07,
"output_cost_per_token": 1.484e-06,
"litellm_provider": "watsonx",
@ -47119,9 +47119,9 @@
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
},
"watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": {
"max_tokens": 128000,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 3.71e-07,
"output_cost_per_token": 1.484e-06,
"litellm_provider": "watsonx",
@ -47168,9 +47168,9 @@
"supports_vision": false
},
"watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": {
"max_tokens": 32000,
"max_tokens": 16384,
"max_input_tokens": 131072,
"max_output_tokens": 32000,
"max_output_tokens": 16384,
"input_cost_per_token": 1.06e-07,
"output_cost_per_token": 3.18e-07,
"litellm_provider": "watsonx",
@ -47193,9 +47193,9 @@
"supports_vision": true
},
"watsonx/openai/gpt-oss-120b": {
"max_tokens": 8192,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"max_output_tokens": 131072,
"input_cost_per_token": 1.59e-07,
"output_cost_per_token": 6.36e-07,
"litellm_provider": "watsonx",