Skip to content

Commit 27c64c9

Browse files
authored
feat: Add 25 new Watson X foundation models (#15219)
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.
1 parent ddb90c9 commit 27c64c9

File tree

1 file changed

+301
-0
lines changed

1 file changed

+301
-0
lines changed

model_prices_and_context_window.json

Lines changed: 301 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -22173,6 +22173,307 @@
2217322173
"supports_tool_choice": true,
2217422174
"supports_vision": false
2217522175
},
22176+
"watsonx/bigscience/mt0-xxl-13b": {
22177+
"max_tokens": 8192,
22178+
"max_input_tokens": 8192,
22179+
"max_output_tokens": 8192,
22180+
"input_cost_per_token": 0.0005,
22181+
"output_cost_per_token": 0.002,
22182+
"litellm_provider": "watsonx",
22183+
"mode": "chat",
22184+
"supports_function_calling": false,
22185+
"supports_parallel_function_calling": false,
22186+
"supports_vision": false
22187+
},
22188+
"watsonx/core42/jais-13b-chat": {
22189+
"max_tokens": 8192,
22190+
"max_input_tokens": 8192,
22191+
"max_output_tokens": 8192,
22192+
"input_cost_per_token": 0.0005,
22193+
"output_cost_per_token": 0.002,
22194+
"litellm_provider": "watsonx",
22195+
"mode": "chat",
22196+
"supports_function_calling": false,
22197+
"supports_parallel_function_calling": false,
22198+
"supports_vision": false
22199+
},
22200+
"watsonx/google/flan-t5-xl-3b": {
22201+
"max_tokens": 8192,
22202+
"max_input_tokens": 8192,
22203+
"max_output_tokens": 8192,
22204+
"input_cost_per_token": 0.0001,
22205+
"output_cost_per_token": 0.00025,
22206+
"litellm_provider": "watsonx",
22207+
"mode": "chat",
22208+
"supports_function_calling": false,
22209+
"supports_parallel_function_calling": false,
22210+
"supports_vision": false
22211+
},
22212+
"watsonx/ibm/granite-13b-chat-v2": {
22213+
"max_tokens": 8192,
22214+
"max_input_tokens": 8192,
22215+
"max_output_tokens": 8192,
22216+
"input_cost_per_token": 0.0005,
22217+
"output_cost_per_token": 0.002,
22218+
"litellm_provider": "watsonx",
22219+
"mode": "chat",
22220+
"supports_function_calling": false,
22221+
"supports_parallel_function_calling": false,
22222+
"supports_vision": false
22223+
},
22224+
"watsonx/ibm/granite-13b-instruct-v2": {
22225+
"max_tokens": 8192,
22226+
"max_input_tokens": 8192,
22227+
"max_output_tokens": 8192,
22228+
"input_cost_per_token": 0.0005,
22229+
"output_cost_per_token": 0.002,
22230+
"litellm_provider": "watsonx",
22231+
"mode": "chat",
22232+
"supports_function_calling": false,
22233+
"supports_parallel_function_calling": false,
22234+
"supports_vision": false
22235+
},
22236+
"watsonx/ibm/granite-3-3-8b-instruct": {
22237+
"max_tokens": 8192,
22238+
"max_input_tokens": 8192,
22239+
"max_output_tokens": 8192,
22240+
"input_cost_per_token": 0.00025,
22241+
"output_cost_per_token": 0.001,
22242+
"litellm_provider": "watsonx",
22243+
"mode": "chat",
22244+
"supports_function_calling": true,
22245+
"supports_parallel_function_calling": true,
22246+
"supports_vision": false
22247+
},
22248+
"watsonx/ibm/granite-4-h-small": {
22249+
"max_tokens": 20480,
22250+
"max_input_tokens": 20480,
22251+
"max_output_tokens": 20480,
22252+
"input_cost_per_token": 0.000625,
22253+
"output_cost_per_token": 0.0025,
22254+
"litellm_provider": "watsonx",
22255+
"mode": "chat",
22256+
"supports_function_calling": true,
22257+
"supports_parallel_function_calling": true,
22258+
"supports_vision": false
22259+
},
22260+
"watsonx/ibm/granite-guardian-3-2-2b": {
22261+
"max_tokens": 8192,
22262+
"max_input_tokens": 8192,
22263+
"max_output_tokens": 8192,
22264+
"input_cost_per_token": 0.00015,
22265+
"output_cost_per_token": 0.0006,
22266+
"litellm_provider": "watsonx",
22267+
"mode": "chat",
22268+
"supports_function_calling": false,
22269+
"supports_parallel_function_calling": false,
22270+
"supports_vision": false
22271+
},
22272+
"watsonx/ibm/granite-guardian-3-3-8b": {
22273+
"max_tokens": 8192,
22274+
"max_input_tokens": 8192,
22275+
"max_output_tokens": 8192,
22276+
"input_cost_per_token": 0.00025,
22277+
"output_cost_per_token": 0.001,
22278+
"litellm_provider": "watsonx",
22279+
"mode": "chat",
22280+
"supports_function_calling": false,
22281+
"supports_parallel_function_calling": false,
22282+
"supports_vision": false
22283+
},
22284+
"watsonx/ibm/granite-ttm-1024-96-r2": {
22285+
"max_tokens": 512,
22286+
"max_input_tokens": 512,
22287+
"max_output_tokens": 512,
22288+
"input_cost_per_token": 0.000625,
22289+
"output_cost_per_token": 0.000625,
22290+
"litellm_provider": "watsonx",
22291+
"mode": "chat",
22292+
"supports_function_calling": false,
22293+
"supports_parallel_function_calling": false,
22294+
"supports_vision": false
22295+
},
22296+
"watsonx/ibm/granite-ttm-1536-96-r2": {
22297+
"max_tokens": 512,
22298+
"max_input_tokens": 512,
22299+
"max_output_tokens": 512,
22300+
"input_cost_per_token": 0.000625,
22301+
"output_cost_per_token": 0.000625,
22302+
"litellm_provider": "watsonx",
22303+
"mode": "chat",
22304+
"supports_function_calling": false,
22305+
"supports_parallel_function_calling": false,
22306+
"supports_vision": false
22307+
},
22308+
"watsonx/ibm/granite-ttm-512-96-r2": {
22309+
"max_tokens": 512,
22310+
"max_input_tokens": 512,
22311+
"max_output_tokens": 512,
22312+
"input_cost_per_token": 0.000625,
22313+
"output_cost_per_token": 0.000625,
22314+
"litellm_provider": "watsonx",
22315+
"mode": "chat",
22316+
"supports_function_calling": false,
22317+
"supports_parallel_function_calling": false,
22318+
"supports_vision": false
22319+
},
22320+
"watsonx/ibm/granite-vision-3-2-2b": {
22321+
"max_tokens": 8192,
22322+
"max_input_tokens": 8192,
22323+
"max_output_tokens": 8192,
22324+
"input_cost_per_token": 0.00015,
22325+
"output_cost_per_token": 0.0006,
22326+
"litellm_provider": "watsonx",
22327+
"mode": "chat",
22328+
"supports_function_calling": false,
22329+
"supports_parallel_function_calling": false,
22330+
"supports_vision": true
22331+
},
22332+
"watsonx/meta-llama/llama-3-2-11b-vision-instruct": {
22333+
"max_tokens": 128000,
22334+
"max_input_tokens": 128000,
22335+
"max_output_tokens": 128000,
22336+
"input_cost_per_token": 0.00025,
22337+
"output_cost_per_token": 0.001,
22338+
"litellm_provider": "watsonx",
22339+
"mode": "chat",
22340+
"supports_function_calling": true,
22341+
"supports_parallel_function_calling": true,
22342+
"supports_vision": true
22343+
},
22344+
"watsonx/meta-llama/llama-3-2-1b-instruct": {
22345+
"max_tokens": 128000,
22346+
"max_input_tokens": 128000,
22347+
"max_output_tokens": 128000,
22348+
"input_cost_per_token": 0.0001,
22349+
"output_cost_per_token": 0.0002,
22350+
"litellm_provider": "watsonx",
22351+
"mode": "chat",
22352+
"supports_function_calling": true,
22353+
"supports_parallel_function_calling": true,
22354+
"supports_vision": false
22355+
},
22356+
"watsonx/meta-llama/llama-3-2-3b-instruct": {
22357+
"max_tokens": 128000,
22358+
"max_input_tokens": 128000,
22359+
"max_output_tokens": 128000,
22360+
"input_cost_per_token": 0.00015,
22361+
"output_cost_per_token": 0.0006,
22362+
"litellm_provider": "watsonx",
22363+
"mode": "chat",
22364+
"supports_function_calling": true,
22365+
"supports_parallel_function_calling": true,
22366+
"supports_vision": false
22367+
},
22368+
"watsonx/meta-llama/llama-3-2-90b-vision-instruct": {
22369+
"max_tokens": 128000,
22370+
"max_input_tokens": 128000,
22371+
"max_output_tokens": 128000,
22372+
"input_cost_per_token": 0.002,
22373+
"output_cost_per_token": 0.008,
22374+
"litellm_provider": "watsonx",
22375+
"mode": "chat",
22376+
"supports_function_calling": true,
22377+
"supports_parallel_function_calling": true,
22378+
"supports_vision": true
22379+
},
22380+
"watsonx/meta-llama/llama-3-3-70b-instruct": {
22381+
"max_tokens": 128000,
22382+
"max_input_tokens": 128000,
22383+
"max_output_tokens": 128000,
22384+
"input_cost_per_token": 0.002,
22385+
"output_cost_per_token": 0.006,
22386+
"litellm_provider": "watsonx",
22387+
"mode": "chat",
22388+
"supports_function_calling": true,
22389+
"supports_parallel_function_calling": true,
22390+
"supports_vision": false
22391+
},
22392+
"watsonx/meta-llama/llama-4-maverick-17b": {
22393+
"max_tokens": 128000,
22394+
"max_input_tokens": 128000,
22395+
"max_output_tokens": 128000,
22396+
"input_cost_per_token": 0.0005,
22397+
"output_cost_per_token": 0.002,
22398+
"litellm_provider": "watsonx",
22399+
"mode": "chat",
22400+
"supports_function_calling": true,
22401+
"supports_parallel_function_calling": true,
22402+
"supports_vision": false
22403+
},
22404+
"watsonx/meta-llama/llama-guard-3-11b-vision": {
22405+
"max_tokens": 128000,
22406+
"max_input_tokens": 128000,
22407+
"max_output_tokens": 128000,
22408+
"input_cost_per_token": 0.00025,
22409+
"output_cost_per_token": 0.001,
22410+
"litellm_provider": "watsonx",
22411+
"mode": "chat",
22412+
"supports_function_calling": false,
22413+
"supports_parallel_function_calling": false,
22414+
"supports_vision": true
22415+
},
22416+
"watsonx/mistralai/mistral-medium-2505": {
22417+
"max_tokens": 128000,
22418+
"max_input_tokens": 128000,
22419+
"max_output_tokens": 128000,
22420+
"input_cost_per_token": 0.00225,
22421+
"output_cost_per_token": 0.00675,
22422+
"litellm_provider": "watsonx",
22423+
"mode": "chat",
22424+
"supports_function_calling": true,
22425+
"supports_parallel_function_calling": true,
22426+
"supports_vision": false
22427+
},
22428+
"watsonx/mistralai/mistral-small-2503": {
22429+
"max_tokens": 32000,
22430+
"max_input_tokens": 32000,
22431+
"max_output_tokens": 32000,
22432+
"input_cost_per_token": 0.0002,
22433+
"output_cost_per_token": 0.0006,
22434+
"litellm_provider": "watsonx",
22435+
"mode": "chat",
22436+
"supports_function_calling": true,
22437+
"supports_parallel_function_calling": true,
22438+
"supports_vision": false
22439+
},
22440+
"watsonx/mistralai/pixtral-12b-2409": {
22441+
"max_tokens": 128000,
22442+
"max_input_tokens": 128000,
22443+
"max_output_tokens": 128000,
22444+
"input_cost_per_token": 0.00015,
22445+
"output_cost_per_token": 0.00015,
22446+
"litellm_provider": "watsonx",
22447+
"mode": "chat",
22448+
"supports_function_calling": false,
22449+
"supports_parallel_function_calling": false,
22450+
"supports_vision": true
22451+
},
22452+
"watsonx/openai/gpt-oss-120b": {
22453+
"max_tokens": 8192,
22454+
"max_input_tokens": 8192,
22455+
"max_output_tokens": 8192,
22456+
"input_cost_per_token": 0.004,
22457+
"output_cost_per_token": 0.016,
22458+
"litellm_provider": "watsonx",
22459+
"mode": "chat",
22460+
"supports_function_calling": false,
22461+
"supports_parallel_function_calling": false,
22462+
"supports_vision": false
22463+
},
22464+
"watsonx/sdaia/allam-1-13b-instruct": {
22465+
"max_tokens": 8192,
22466+
"max_input_tokens": 8192,
22467+
"max_output_tokens": 8192,
22468+
"input_cost_per_token": 0.0005,
22469+
"output_cost_per_token": 0.002,
22470+
"litellm_provider": "watsonx",
22471+
"mode": "chat",
22472+
"supports_function_calling": false,
22473+
"supports_parallel_function_calling": false,
22474+
"supports_vision": false
22475+
},
22476+
2217622477
"whisper-1": {
2217722478
"input_cost_per_second": 0.0001,
2217822479
"litellm_provider": "openai",

0 commit comments

Comments
 (0)