> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# IBM WatsonX

> Use IBM WatsonX foundation models with Agno agents.

IBM WatsonX provides access to foundation models through IBM's cloud platform.

See all the IBM WatsonX supported models [here](https://www.ibm.com/products/watsonx-ai/foundation-models).

* We recommend using `meta-llama/llama-3-3-70b-instruct` for general use
* We recommend `ibm/granite-20b-code-instruct` for code-related tasks
* We recommend using `meta-llama/llama-3-2-11b-vision-instruct` for image understanding

## Multimodal Support

With WatsonX we support `Image` as input.

## Installation

```bash theme={null}
uv pip install -U ibm-watsonx-ai agno
```

## Authentication

Set your `IBM_WATSONX_API_KEY` and `IBM_WATSONX_PROJECT_ID` environment variables. Get your credentials from [IBM Cloud](https://cloud.ibm.com/).
You can also set the `IBM_WATSONX_URL` environment variable to the URL of the WatsonX API you want to use. It defaults to `https://eu-de.ml.cloud.ibm.com`.

<CodeGroup>
  ```bash Mac theme={null}
  export IBM_WATSONX_API_KEY=***
  export IBM_WATSONX_PROJECT_ID=***
  ```

  ```bash Windows theme={null}
  setx IBM_WATSONX_API_KEY ***
  setx IBM_WATSONX_PROJECT_ID ***
  ```
</CodeGroup>

## Example

Use `WatsonX` with your `Agent`:

<CodeGroup>
  ```python agent.py theme={null}
  from agno.agent import Agent
  from agno.models.ibm import WatsonX

  agent = Agent(
      model=WatsonX(id="meta-llama/llama-3-3-70b-instruct"),
      markdown=True
  )

  # Print the response in the terminal
  agent.print_response("Share a 2 sentence horror story.")

  ```
</CodeGroup>

<Note> View more examples [here](/models/providers/cloud/ibm-watsonx/usage/basic-stream). </Note>

## Params

| Parameter           | Type                       | Default                            | Description                                                                    |
| ------------------- | -------------------------- | ---------------------------------- | ------------------------------------------------------------------------------ |
| `id`                | `str`                      | `"ibm/granite-20b-code-instruct"`  | The id of the IBM watsonx model to use                                         |
| `name`              | `str`                      | `"WatsonX"`                        | The name of the model                                                          |
| `provider`          | `str`                      | `"IBM"`                            | The provider of the model                                                      |
| `frequency_penalty` | `Optional[float]`          | `None`                             | Penalizes new tokens based on their frequency in the text so far               |
| `presence_penalty`  | `Optional[float]`          | `None`                             | Penalizes new tokens based on whether they appear in the text so far           |
| `max_tokens`        | `Optional[int]`            | `None`                             | Maximum number of tokens to generate                                           |
| `temperature`       | `Optional[float]`          | `None`                             | Controls randomness in the model's output                                      |
| `top_p`             | `Optional[float]`          | `None`                             | Controls diversity via nucleus sampling                                        |
| `logprobs`          | `Optional[int]`            | `None`                             | Return log probabilities of the output tokens                                  |
| `top_logprobs`      | `Optional[int]`            | `None`                             | Number of most likely tokens to return log probabilities for                   |
| `request_params`    | `Optional[Dict[str, Any]]` | `None`                             | Additional parameters to include in the request                                |
| `api_key`           | `Optional[str]`            | `None`                             | The API key for IBM watsonx (defaults to IBM\_WATSONX\_API\_KEY env var)       |
| `project_id`        | `Optional[str]`            | `None`                             | The project ID for IBM watsonx (defaults to IBM\_WATSONX\_PROJECT\_ID env var) |
| `url`               | `Optional[str]`            | `"https://eu-de.ml.cloud.ibm.com"` | The watsonx endpoint URL (IBM\_WATSONX\_URL env var takes precedence)          |
| `verify`            | `bool`                     | `True`                             | Verify TLS certificates when connecting                                        |
| `client_params`     | `Optional[Dict[str, Any]]` | `None`                             | Additional parameters for client configuration                                 |

`WatsonX` is a subclass of the [Model](/reference/models/model) class and has access to the same params.