> 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.

# Replicate (gateway)

> Set up Replicate with the Respan gateway.

Route Replicate calls through the Respan gateway only after the model is configured for your project and you have added your own Replicate credentials (BYOK). Provider usage is billed to your Replicate account, not Respan credits.

## Setup

> **Note**
>
> No Replicate models are currently listed in the public Gateway model catalog. Confirm that your project has a configured Replicate model before using this example. For direct Replicate calls with Respan observability, see the [Replicate integration](/docs/integrations/replicate).

#### Install packages

```bash
pip install openai
```

#### Set environment variables

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

#### 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_REPLICATE_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_REPLICATE_MODEL_ID", messages=messages)
response = client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
```

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