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

feat: Add 25 new Watson X foundation models (#15219)

Browse source 
Added comprehensive Watson X model support including:
- IBM Granite models (granite-4-h-small, granite-3-3-8b-instruct, granite-guardian variants, granite-vision, granite-ttm time series models)
- Meta Llama models (llama-3-2-1b/3b/11b-vision/90b-vision, llama-3-3-70b, llama-4-maverick-17b, llama-guard-3-11b-vision)
- Mistral models (mistral-medium-2505, mistral-small-2503, pixtral-12b-2409)
- Additional models (BigScience mt0-xxl-13b, Google flan-t5-xl-3b, OpenAI gpt-oss-120b, SDAIA allam-1-13b-instruct, Core42 jais-13b-chat)

All models include proper pricing, token limits, and capability flags (function calling, vision support, etc.) based on IBM Watson X documentation.
This commit is contained in:
Gal Bloch 2025-10-06 22:33:05 +03:00 • committed by GitHub
parent ddb90c9ad7
commit 27c64c90dc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 301 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

301
model_prices_and_context_window.json
View file

@ -22173,6 +22173,307 @@
"supports_tool_choice": true,
"supports_vision": false
},
"watsonx/bigscience/mt0-xxl-13b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/core42/jais-13b-chat": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/google/flan-t5-xl-3b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0001,
"output_cost_per_token": 0.00025,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-13b-chat-v2": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-13b-instruct-v2": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-3-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00025,
"output_cost_per_token": 0.001,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/ibm/granite-4-h-small": {
"max_tokens": 20480,
"max_input_tokens": 20480,
"max_output_tokens": 20480,
"input_cost_per_token": 0.000625,
"output_cost_per_token": 0.0025,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/ibm/granite-guardian-3-2-2b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.0006,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-guardian-3-3-8b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00025,
"output_cost_per_token": 0.001,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-ttm-1024-96-r2": {
"max_tokens": 512,
"max_input_tokens": 512,
"max_output_tokens": 512,
"input_cost_per_token": 0.000625,
"output_cost_per_token": 0.000625,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-ttm-1536-96-r2": {
"max_tokens": 512,
"max_input_tokens": 512,
"max_output_tokens": 512,
"input_cost_per_token": 0.000625,
"output_cost_per_token": 0.000625,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-ttm-512-96-r2": {
"max_tokens": 512,
"max_input_tokens": 512,
"max_output_tokens": 512,
"input_cost_per_token": 0.000625,
"output_cost_per_token": 0.000625,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/ibm/granite-vision-3-2-2b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.0006,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": true
},
"watsonx/meta-llama/llama-3-2-11b-vision-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00025,
"output_cost_per_token": 0.001,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
},
"watsonx/meta-llama/llama-3-2-1b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.0001,
"output_cost_per_token": 0.0002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/meta-llama/llama-3-2-3b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.0006,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/meta-llama/llama-3-2-90b-vision-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.002,
"output_cost_per_token": 0.008,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
},
"watsonx/meta-llama/llama-3-3-70b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.002,
"output_cost_per_token": 0.006,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/meta-llama/llama-4-maverick-17b": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/meta-llama/llama-guard-3-11b-vision": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00025,
"output_cost_per_token": 0.001,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": true
},
"watsonx/mistralai/mistral-medium-2505": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00225,
"output_cost_per_token": 0.00675,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/mistralai/mistral-small-2503": {
"max_tokens": 32000,
"max_input_tokens": 32000,
"max_output_tokens": 32000,
"input_cost_per_token": 0.0002,
"output_cost_per_token": 0.0006,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false
},
"watsonx/mistralai/pixtral-12b-2409": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.00015,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": true
},
"watsonx/openai/gpt-oss-120b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.004,
"output_cost_per_token": 0.016,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"watsonx/sdaia/allam-1-13b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0005,
"output_cost_per_token": 0.002,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
},
"whisper-1": {
"input_cost_per_second": 0.0001,
"litellm_provider": "openai",