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

# Smolagents (gateway)

> Set up Smolagents with the Respan gateway.

Route Smolagents' underlying LLM calls through the Respan gateway to use 1000+ models from different providers. Only your `RESPAN_API_KEY` is needed — no separate provider keys required.

## Setup

#### Install packages

```bash
pip install smolagents litellm
```

#### Set environment variables

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

No `OPENAI_API_KEY` needed — the Respan gateway handles provider authentication.

#### Point Smolagents to the Respan gateway

```python
import os
from smolagents import CodeAgent, LiteLLMModel

model = LiteLLMModel(
    model_id="openai/gpt-5.5",
    api_key=os.environ["RESPAN_API_KEY"],
    api_base="https://api.respan.ai/api",
)

agent = CodeAgent(tools=[], model=model)
print(agent.run("What is the capital of France?"))
```

## Switch models

Use another OpenAI model ID through the same gateway-backed LiteLLM model wrapper.

```python
LiteLLMModel(model_id="openai/gpt-5.5", api_key=..., api_base="https://api.respan.ai/api")
LiteLLMModel(model_id="openai/gpt-5-mini", api_key=..., api_base="https://api.respan.ai/api")
```

> **Note**
>
> Smolagents uses LiteLLM provider namespaces. This page avoids showing Claude or Gemini behind an `openai/` prefix; use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

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