Getting foundation model information

Last updated: Feb 21, 2025

Get a list of the foundation models deployed in watsonx.ai and filter the list in useful ways.

Ways to develop

You can get information about the available foundation models by using these programming methods:

Alternatively, you can see the list of foundation models and filter them from the Resource hub in the watsonx.ai UI. For details, see the following resources:

REST API

You can use the List the available foundation models method of the watsonx.ai API to get information about the available foundation models.

The model information that is returned includes the model ID, which you need to reference the model from your code.

List the available foundation models

The List the available foundation models method in the watsonx.ai API gets information about the foundation models that are deployed by IBM in watsonx.ai and are available for inferencing immediately.

curl -X GET \
  'https://{region}.ml.cloud.ibm.com/ml/v1/foundation_model_specs?version=2024-05-01'

After you get the model ID, you can reference the model ID in your code like this:

curl --request POST 'https://{cluster_url}/ml/v1/text/generation?version=2023-05-02'
-H 'Authorization: Bearer eyJhbGciOiJSUzUxM...'
-H 'Content-Type: application/json'
-H 'Accept: application/json'
--data-raw '{
  "model_id": "google/flan-t5-xxl",
  "input": "Tell me a story",
  "project_id": "63dc4cf1-252f-424b-b52d-5cdd9814987f"
}'

List the custom foundation models

To get a list of deployed custom foundation models that you can access, use the following method. This method requires a bearer token.

curl -X GET \
  'https://{region}.ml.cloud.ibm.com/ml/v4/deployments?version=2024-12-12&type=custom_foundation_model'

List the deploy on demand models

To get a list of IBM-provided foundation models that you can deploy yourself, use the following method:

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

Use the returned Model ID to deploy the deploy on demand foundation model to a deployment space. After you deploy the model, you can inference the model by using the API endpoint for your deployment.

Finding model IDs for inferencing the provided foundation models

To find the model IDs for provided foundation models, follow these links:

Model IDs for deploy on demand foundation models

Attention: Remember, you do not inference a deploy on demand foundation model by its model ID. You use the model ID only to deploy the model. After you deploy the model, you can inference the model by using the API endpoint for your deployment.

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.

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

deepseek-r1-distill-llama-8b

deepseek-ai/deepseek-r1-distill-llama-8b-curated

deepseek-r1-distill-llama-70b

deepseek-ai/deepseek-r1-distill-llama-70b-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