Foundation model IDs

Last updated: Dec 13, 2024

When you write code that interacts with a foundation model, you need to reference the foundation model by its model ID.

You can reference a foundation model by its model ID when you do the following things:

Inference a foundation model that is deployed by IBM. See Foundation model IDs for inferencing from the API.
Deploy a deploy on demand foundation model. See Foundation model IDs for deploying from the API.

Foundation model IDs for inferencing from the API

Use the List the available foundation models REST method to get the {model_id} for a foundation model, and then specify the model ID as a string in your code.

For information about how to get model IDs by using the Python library, see Getting information about available foundation models programmatically.

Model IDs for inferencing

The following list shows the values to use in the {model_id} parameter when you inference a foundation model that is deployed by IBM from the API.

For the model IDs for deploy on demand foundation models, see Foundation model IDs for deploying from the API. To inference a deploy on demand foundation model by using the API, you must specify the deployment ID for the model, not the model ID.

all-minilm-l6-v2
```
sentence-transformers/all-minilm-l6-v2
```

all-minilm-l12-v2

sentence-transformers/all-minilm-l12-v2

allam-1-13b-instruct
```
sdaia/allam-1-13b-instruct
```
codellama-34b-instruct-hf
```
codellama/codellama-34b-instruct-hf
```

elyza-japanese-llama-2-7b-instruct

elyza/elyza-japanese-llama-2-7b-instruct

flan-t5-xxl-11b
```
google/flan-t5-xxl
```
flan-ul2-20b
```
google/flan-ul2
```
granite-7b-lab
```
ibm/granite-7b-lab
```
granite-8b-japanese
```
ibm/granite-8b-japanese
```
granite-13b-chat-v2
```
ibm/granite-13b-chat-v2
```
granite-13b-instruct-v2
```
ibm/granite-13b-instruct-v2
```
granite-20b-multilingual
```
ibm/granite-20b-multilingual
```
granite-3-2b-instruct
```
ibm/granite-3-2b-instruct
```
granite-3-8b-instruct
```
ibm/granite-3-8b-instruct
```
granite-guardian-3-2b
```
ibm/granite-guardian-3-2b
```
granite-guardian-3-8b
```
ibm/granite-guardian-3-8b
```
granite-3b-code-instruct
```
ibm/granite-3b-code-instruct
```
granite-8b-code-instruct
```
ibm/granite-8b-code-instruct
```
granite-20b-code-instruct
```
ibm/granite-20b-code-instruct
```
granite-34b-code-instruct
```
ibm/granite-34b-code-instruct
```
jais-13b-chat
```
core42/jais-13b-chat
```
llama-3-3-70b-instruct
```
meta-llama/llama-3-3-70b-instruct
```
llama-3-2-1b-instruct
```
meta-llama/llama-3-2-1b-instruct
```
llama-3-2-3b-instruct
```
meta-llama/llama-3-2-3b-instruct
```

llama-3-2-11b-vision-instruct

meta-llama/llama-3-2-11b-vision-instruct

llama-3-2-90b-vision-instruct

meta-llama/llama-3-2-90b-vision-instruct

llama-guard-3-11b-instruct
```
meta-llama/llama-guard-3-11b-vision
```
llama-3-1-8b-instruct
```
meta-llama/llama-3-1-8b-instruct
```
llama-3-1-70b-instruct
```
meta-llama/llama-3-1-70b-instruct
```
llama-3-405b-instruct
```
meta-llama/llama-3-405b-instruct
```
llama-3-8b-instruct
```
meta-llama/llama-3-8b-instruct
```
llama-3-70b-instruct
```
meta-llama/llama-3-70b-instruct
```
llama-2-13b-chat
```
meta-llama/llama-2-13b-chat
```
llama-2-70b-chat
```
meta-llama/llama-2-70b-chat
```
llama2-13b-dpo-v7
```
mnci/llama2-13b-dpo-v7
```
mistral-large
```
mistralai/mistral-large
```
mixtral-8x7b-instruct-v01
```
mistralai/mixtral-8x7b-instruct-v01
```
ms-marco-minilm-l-12-v2
```
cross-encoder/ms-marco-minilm-l-12-v2
```
mt0-xxl-13b
```
bigscience/mt0-xxl
```
multilingual-e5-large
```
intfloat/multilingual-e5-large
```
pixtral-12b
```
mistralai/pixtral-12b
```
slate-30m-english-rtrvr
```
ibm/slate-30m-english-rtrvr
```
slate-30m-english-rtrvr-v2
```
ibm/slate-30m-english-rtrvr-v2
```
slate-125m-english-rtrvr
```
ibm/slate-30m-english-rtrvr
```
slate-125m-english-rtrvr-v2
```
ibm/slate-30m-english-rtrvr-v2
```

Foundation model IDs for deploying from the API

To programmatically get a list of foundation models that can be deployed on demand, specify the filters=curated parameter when you submit a List the available foundation models method REST API request.

For example:

curl -X GET \
  'https://{region}.ml.cloud.ibm.com/ml/v1/foundation_model_specs?version=2024-12-10&filters=curated'

From the watsonx.ai REST API, you can use the Create a deployment method to deploy the foundation model, and then use the Deployments > Infer text method to inference your deployed foundation model.

For more information, see Deploying and managing foundation models deployed on-demand with REST API.

Model IDs for deploying

The following list shows the values to use in the {model_id} parameter when you deploy a deploy on demand foundation model from the API.

granite-3-8b-base
```
ibm/granite-3-8b-base-curated
```
granite-13b-chat-v2
```
ibm/granite-13b-chat-v2-curated
```
granite-13b-instruct-v2
```
ibm/granite-13b-instruct-v2-curated
```

granite-20b-code-base-schema-linking

ibm/granite-20b-code-base-schema-linking-curated

granite-20b-code-base-sql-gen

ibm/granite-20b-code-base-sql-gen-curated

flan-t5-xl-3b
```
google/flan-t5-xl-curated
```
flan-t5-xxl-11b
```
google/flan-t5-xxl-curated
```
flan-ul2-20b
```
google/flan-ul2-curated
```
llama-2-13b-chat
```
meta-llama/llama-2-13b-chat-curated
```
llama-2-70b-chat
```
meta-llama/llama-2-70b-chat-curated
```
llama-3-8b-instruct
```
meta-llama/llama-3-8b-instruct-curated
```

llama-3-70b-instruct

meta-llama/llama-3-70b-instruct-curated

llama-3-1-8b
```
meta-llama/llama-3-1-8b-curated
```

llama-3-1-8b-instruct

meta-llama/llama-3-1-8b-instruct-curated

llama-3-3-70b-instruct

meta-llama/llama-3-3-70b-instruct-curated

llama-3-3-70b-instruct-hf

meta-llama/llama-3-3-70b-instruct-hf-curated

mixtral-8x7b-base
```
mistralai/mixtral-8x7b-base-curated
```

mixtral-8x7b-instruct-v01

mistralai/mixtral-8x7b-instruct-v01-curated

mistral-nemo-instruct-2407

mistralai/mistral-nemo-instruct-2407-curated

mt0-xxl-13b
```
bigscience/mt0-xxl-curated
```

Parent topic: Coding generative AI solutions