> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server.

# Watsonx (gateway)

> Set up IBM watsonx.ai with the Respan gateway.

Route Watsonx calls through the Respan gateway with an OpenAI-compatible client. This setup uses your `RESPAN_API_KEY`; your application does not need to manage IBM Watsonx credentials directly.

Use a Watsonx model ID from your [Respan model list](https://platform.respan.ai/platform/models). If your workspace uses a custom Watsonx deployment, use the model name shown in the platform.

## Setup

#### Install packages

```bash
pip install openai
```

#### Set environment variables

```bash
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
```

No `WATSONX_API_KEY` is required in your application for gateway calls. The Respan gateway handles provider authentication and request logging.

#### Point an OpenAI-compatible client to the Respan gateway

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RESPAN_API_KEY"],
    base_url="https://api.respan.ai/api",
)

response = client.chat.completions.create(
    model="YOUR_WATSONX_MODEL_ID",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response.choices[0].message.content)
```

## Switch models

Change the `model` parameter to use 1000+ models from different providers through the same gateway.

```python
response = client.chat.completions.create(model="YOUR_WATSONX_MODEL_ID", messages=messages)
response = client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
response = client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)
```

See the [full model list](https://platform.respan.ai/platform/models).