You can work with foundation models in IBM watsonx.ai programmatically by using the watsonx.ai API.
See the API reference documentation.
You can also use the REST API to perform the following tasks:
- Get foundation model information
- Inference foundation models
- Add generative chat to your applications with the chat API
- Build agent-driven chat workflows
- Extract text from documents
- Prompt tuning a foundation model
- Vectorize text
- Rerank document passages
- Forecast future values
Prerequisites
For quick access to the following information, open the Developer access page:
- Base URL for API endpoints
- Project or space ID
To open the page, from the watsonx.ai home page for the project or space that you want to work with, open the Navigation Menu 
,
and then click Developer access.
You also need the following information to submit REST API requests:
-
To use the watsonx.ai API, you need a bearer token. See Credentials for programmatic access.
-
You must specify the
{model_id}for the foundation model that you want to use. See Getting information about available foundation models. -
Specify the date on which you created and tested your code in the version parameter that is required with each request. For example,
version=2025-02-06.
Some tasks require you to reference data that is made available as a data connection. For more information about how to add a file, and then reference a file from the API, see Adding files to reference from the API.
If you want help with formatting an inference request in the API, you can submit the same request from the Prompt Lab. From the code panel of Prompt Lab, which shows the cURL request that is generated by your prompt, you can check the syntax that is used.
Parent topic: Coding generative AI solutions