notification

Free token limit increased!

New 300k token limit for all new, free trials to use for LLM API calls and more. Sign up for free here.

Featured foundation models

Getting started

A collection of open source and IBM models are deployed in IBM watsonx.ai. You can interact with the deployed foundation models programmatically. Click on a provider to learn more about the supported models that IBM provides. The tables in the following sections give details on models IBM provides, including model ID, token limits, and pricing.

Overview

A collection of open source and IBM foundation models are deployed in IBM watsonx.ai. You can prompt the deployed foundation models programmatically.

To understand how the model provider, instruction tuning, token limits, and other factors can affect which model to choose, see Choosing a foundation model.

Listing available models programmatically

You can use the List the available foundation models method to return all the foundation models, including Tech Preview models.

Replace {token} and {watsonx_ai_url} with values from your account.

1curl -X GET \
2-H "Authorization: Bearer {token}" \
3-H "Content-Type: application/json" \
4-H "Accept: application/json" \
5"{watsonx_ai_url}/ml/v1/foundation_model_specs?version=2024-05-31&tech_preview=true"

After you find the model you want to use, copy the Model ID.

Supporting your use cases

To understand how models can address your use case, including information on model modalities, supported languages, tuning, and indemnification, see our product documentation on choosing a model.

Some IBM foundation models are also available from Hugging Face. License terms for IBM models that you access from Hugging Face are available from the Hugging Face website. For more information about contractual protections related to IBM indemnification for IBM foundation models that you access in watsonx.ai, see the IBM Client Relationship Agreement and IBM watsonx.ai service description.

Supported API functionality by model

Model	Model ID	Text Generation	Chat Completion	Tool Calling	Vision
granite-3-3-8b-instruct	`ibm/granite-3-3-8b-instruct` Copied!	✅	✅	✅
granite-13b-instruct-v2	`ibm/granite-13b-instruct-v2` Copied!	✅	✅	✅
granite-8b-japanese (Deprecated)	`ibm/granite-8b-japanese` Copied!	✅
granite-3-8b-base	`ibm/granite-3-8b-base` Copied!	✅
granite-3-2b-instruct	`ibm/granite-3-2b-instruct` Copied!	✅	✅	✅
granite-3-8b-instruct	`ibm/granite-3-8b-instruct` Copied!	✅	✅	✅
granite-3-2-8b-instruct	`ibm/granite-3-2-8b-instruct` Copied!	✅	✅	✅
granite-guardian-3-2b	`ibm/granite-guardian-3-2b` Copied!	✅	✅	✅
granite-guardian-3-8b	`ibm/granite-guardian-3-8b` Copied!	✅	✅	✅
granite-3b-code-instruct (Deprecated)	`ibm/granite-3b-code-instruct` Copied!	✅
granite-8b-code-instruct	`ibm/granite-8b-code-instruct` Copied!	✅
granite-20b-code-instruct (Deprecated)	`ibm/granite-20b-code-instruct` Copied!	✅
granite-34b-code-instruct (Deprecated)	`ibm/granite-34b-code-instruct` Copied!	✅
granite-vision-3-2-2b	`ibm/granite-vision-3-2-2b` Copied!				✅
flan-t5-xl-3b	`google/flan-t5-xl` Copied!	✅	✅
flan-t5-xxl-11b	`google/flan-t5-xxl` Copied!	✅	✅
flan-ul2-20b	`google/flan-ul2` Copied!	✅	✅
llama-4-maverick-17b-128e-instruct-fp8	`meta-llama/llama-4-maverick-17b-128e-instruct-fp8` Copied!	✅	✅	✅
llama-4-scout-17b-16e-instruct Beta	`meta-llama/llama-4-scout-17b-16e-instruct` Copied!	✅	✅	✅
llama-3-3-70b-instruct	`meta-llama/llama-3-3-70b-instruct` Copied!	✅	✅	✅
llama-3-2-1b-instruct	`meta-llama/llama-3-2-1b-instruct` Copied!	✅	✅
llama-3-2-3b-instruct	`meta-llama/llama-3-2-3b-instruct` Copied!	✅	✅
llama-3-2-11b-vision-instruct	`meta-llama/llama-3-2-11b-vision-instruct` Copied!	✅	✅	✅	✅
llama-3-2-90b-vision-instruct	`meta-llama/llama-3-2-90b-vision-instruct` Copied!	✅	✅	✅	✅
llama-guard-3-11b-vision-instruct	`meta-llama/llama-guard-3-11b-vision` Copied!	✅	✅	✅	✅
llama-3-1-8b-instruct (Deprecated)	`meta-llama/llama-3-1-8b-instruct` Copied!	✅	✅
llama-3-1-70b-instruct (Deprecated)	`meta-llama/llama-3-1-70b-instruct` Copied!	✅	✅
llama-2-13b-chat (Deprecated)	`meta-llama/llama-2-13b-chat` Copied!	✅	✅
mistral-small-3-1-24b-instruct-2503	`mistralai/mistral-small-3-1-24b-instruct-2503` Copied!	✅	✅
mistral-large	`mistralai/mistral-large` Copied!	✅	✅	✅
mistral-medium-2505	`mistralai/mistral-medium-2505` Copied!	✅	✅	✅
mistral-small-24b-instruct-2501 (Deprecated)	`mistralai/mistral-small-24b-instruct-2501` Copied!	✅	✅
mixtral-8x7b-instruct-v01 (Deprecated)	`mistralai/mixtral-8x7b-instruct-v01` Copied!	✅	✅	✅
pixtral-12b	`mistralai/pixtral-12b` Copied!	✅	✅	✅
elyza-japanese-llama-2-7b-instruct	`elyza/elyza-japanese-llama-2-7b-instruct` Copied!	✅	✅
jais-13b-chat	`core42/jais-13b-chat` Copied!	✅	✅
allam-1-13b-instruct	`sdaia/allam-1-13b-instruct` Copied!	✅	✅

IBM foundation models

IBM Granite

Model Name	Model ID	Max Tokens (input + output)	Input Price (USD/1,000 tokens)	Output Price (USD/1,000 tokens)
granite-3-3-8b-instruct	`ibm/granite-3-3-8b-instruct` Copied!	131,072	$0.0002	$0.0002
granite-13b-instruct-v2	`ibm/granite-13b-instruct-v2` Copied!	8,192	$0.0006	$0.0006
granite-8b-japanese	`ibm/granite-8b-japanese` Copied!	4,096	$0.0006	$0.0006
granite-3-8b-base	`ibm/granite-3-8b-base` Copied!	4,096	$0.0006	$0.0006
granite-3-2b-instruct	`ibm/granite-3-2b-instruct` Copied!	131,072	$0.0001	$0.0001
granite-3-8b-instruct	`ibm/granite-3-8b-instruct` Copied!	131,072	$0.0002	$0.0002
granite-3-2-8b-instruct	`ibm/granite-3-2-8b-instruct` Copied!	131,072	$0.0002	$0.0002
granite-guardian-3-2b	`ibm/granite-guardian-3-2b` Copied!	131,072	$0.0001	$0.0001
granite-guardian-3-8b	`ibm/granite-guardian-3-8b` Copied!	131,072	$0.0002	$0.0002
granite-3b-code-instruct	`ibm/granite-3b-code-instruct` Copied!	128,000	$0.0006	$0.0006
granite-8b-code-instruct	`ibm/granite-8b-code-instruct` Copied!	128,000	$0.0006	$0.0006
granite-20b-code-instruct	`ibm/granite-20b-code-instruct` Copied!	8,192	$0.0006	$0.0006
granite-34b-code-instruct	`ibm/granite-34b-code-instruct` Copied!	8,192	$0.0006	$0.0006
granite-vision-3-2-2b	`ibm/granite-vision-3-2-2b` Copied!	131,072	$0.0001	$0.0001

Third Party Foundation Models

SDAIA ALLaM

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
allam-1-13b-instruct	`sdaia/allam-1-13b-instruct` Copied!	4,096	$0.0018	$0.0018

Code Llama

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
codellama-34b-instruct	`codellama/codellama-34b-instruct-hf` Copied!	16,384	$0.0018	$0.0018

Core 42

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
jais-13b-chat	`core42/jais-13b-chat` Copied!	2,048	$0.0018	$0.0018

Elyza

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
elyza-japanese-llama-2-7b-instruct	`elyza/elyza-japanese-llama-2-7b-instruct` Copied!	4,096	$0.0018	$0.0018

Google Flan

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
flan-t5-xl-3b	`google/flan-t5-xl` Copied!	4,096	$0.0006	$0.0006
flan-t5-xxl-11b	`google/flan-t5-xxl` Copied!	4,096	$0.0018	$0.0018
flan-ul2-20b	`google/flan-ul2` Copied!	4,096	$0.0050	$0.0050

Meta Llama

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
llama-3-2-1b-instruct	`meta-llama/llama-3-2-1b-instruct` Copied!	131,072	$0.0001	$0.0001
llama-3-2-3b-instruct	`meta-llama/llama-3-2-3b-instruct` Copied!	131,072	$0.00015	$0.00015
llama-3-2-11B-vision-instruct	`meta-llama/llama-3-2-11b-vision-instruct` Copied!	131,072	$0.00035	$0.00035
llama-3-2-90B-vision-instruct	`meta-llama/llama-3-2-90b-vision-instruct` Copied!	131,072	$0.0020	$0.0020
llama-guard-3-11B-vision-instruct	`meta-llama/llama-guard-3-11b-vision` Copied!	131,072	$0.00035	$0.00035
llama3-llava-next-8b-hf (Deprecated)	`meta-llama/llama3-llava-next-8b-hf` Copied!	8,192	$0.0006	$0.0006
llama-3-1-8b-instruct	`meta-llama/llama-3-1-8b-instruct` Copied!	131,072	$0.0006	$0.0006
llama-3-1-70b-instruct	`meta-llama/llama-3-1-70b-instruct` Copied!	131,072	$0.0018	$0.0018
llama-3-405b-instruct	`meta-llama/llama-3-405b-instruct` Copied!	16,384	$0.0050	$0.0160
llama-3-8b-instruct	`meta-llama/llama-3-8b-instruct` Copied!	8,192	$0.0006	$0.0006
llama-3-70b-instruct	`meta-llama/llama-3-70b-instruct` Copied!	8,192	$0.0018	$0.0018
llama-2-13b-chat (Deprecated)	`meta-llama/llama-2-13b-chat` Copied!	4,096	$0.0006	$0.0006
llama2-13b-dpo-v7	`mnci/llama2-13b-dpo-v7` Copied!	4,096	$0.0018	$0.0018

Mistral

Model Name	Model ID	Max Tokens	Input Price (per 1K tokens)	Output Price (per 1K tokens)
mistral-small	`mistralai/mistral-small-24b-instruct-2501` Copied!	32,768	$0.00035	$0.00035
mistral-large	`mistralai/mistral-large` Copied!	32,768	$0.0100	$0.0100
mixtral-8x7b-instruct-v01	`mistralai/mixtral-8x7b-instruct-v01` Copied!	32,768	$0.0006	$0.0006

IBM Embedding Models

IBM Slate

Model Name	Model ID	Max Input Tokens	Dimensions	Price (per 1K tokens)
slate-125m-english-rtrvr-v2	`ibm/slate-125m-english-rtrvr-v2` Copied!	512	768	$0.0001
slate-125m-english-rtrvr	`ibm/slate-125m-english-rtrvr` Copied!	512	768	$0.0001
slate-30m-english-rtrvr-v2	`ibm/slate-30m-english-rtrvr-v2` Copied!	512	384	$0.0001
slate-30m-english-rtrvr	`ibm/slate-30m-english-rtrvr` Copied!	512	384	$0.0001

Third Party Embedding Models

Sentence Transformers

Model Name	Model ID	Provider	Max Input Tokens	Dimensions	Price (per 1K tokens)
all-minilm-l12-v2	`sentence-transformers/all-minilm-l12-v2` Copied!	Sentence Transformers	256	384	$0.0001

Multilingual E5

Model Name	Model ID	Provider	Max Input Tokens	Dimensions	Price (per 1K tokens)
multilingual-e5-large	`intfloat/multilingual-e5-large` Copied!	Microsoft	512	1,024	$0.0001

IBM Time Series Models

IBM Granite Time Series

Model Name	Model ID	Max Data Points	Input Price (per 1K pts)	Output Price (per 1K pts)
granite-ttm-512-96-r2	`ibm/granite-ttm-512-96-r2` Copied!	608	$0.13	$0.38
granite-ttm-1024-96-r2	`ibm/granite-ttm-1024-96-r2` Copied!	1120	$0.13	$0.38
granite-ttm-1536-96-r2	`ibm/granite-ttm-1536-96-r2` Copied!	1536	$0.13	$0.38

Note: The max data points limit for timeseries models is per combination of a channel and ID for multivariate forecasting, meaning the model can process a combination of # of channels X # of IDs # Max Data Points

Third Party Re-rank Models

MS Marco

Model Name	Model ID	Max Documents	Price (per 1K tokens)
ms-marco-MiniLM-L-12-v2	`cross-encoder/ms-marco-MiniLM-L-12-v2` Copied!	50	$0.000005

Edit this page on GitHub

Get started: Quickstart

Get started: Libraries

Models

Featured foundation models

Granite

Provider: IBM

Llama

Provider: Meta

Mistral AI

Provider: Mistral AI

Getting started

AlLaM

Code Llama

Core42

Elyza

Google Flan

IBM Granite

Meta Llama

Mistral AI

mT0

IBM Slate

OpenSource NLP and CV Community

Microsoft

IBM Granite

MS Macro

Overview

Listing available models programmatically

Supporting your use cases

Supported API functionality by model

IBM foundation models

IBM Granite

Third Party Foundation Models

SDAIA ALLaM

Code Llama

Core 42

Elyza

Google Flan

Meta Llama

Mistral

IBM Embedding Models

IBM Slate

Third Party Embedding Models

Sentence Transformers

Multilingual E5

IBM Time Series Models

IBM Granite Time Series

Third Party Re-rank Models

MS Marco