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

# Regions

> Configure the region and authentication for the Toqan Router HTTP API.

Use the **Toqan Router** HTTP API directly, or configure an OpenAI-compatible client.

| Region | Base URL |
| - | - |
| Frankfurt | `https://router.toqan.ai/eu` |
| São Paulo | `https://router.toqan.ai/br` |

Keep the regional prefix in every request. Use an API key from the selected region and a model enabled in the workspace.

```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}}
export TOQAN_BASE_URL="https://router.toqan.ai/eu"
export TOQAN_API_KEY="<api-key>"

curl "$TOQAN_BASE_URL/v3/router/chat/completions" \
  -H "Authorization: Bearer $TOQAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4.1-mini","messages":[{"role":"user","content":"Hello"}]}'
```

For São Paulo, replace `/eu` with `/br`.

## OpenAI-compatible clients

Set `baseURL` (Node.js) or `base_url` (Python) to the regional URL followed by `/v3/router`. Pass the API key as `apiKey` or `api_key`.

## Timeouts and retries

Configure the request timeout in the HTTP client. For streaming, keep the connection open while receiving events. See [Retries](/docs/ai-gateway/features/retries.md) for gateway retry options.

## OpenTelemetry

Set `OTEL_EXPORTER_OTLP_ENDPOINT` to the regional URL followed by `/v2/otel`.

[API keys](/docs/ai-gateway/configuration/api-keys.md) · [API errors](/docs/reference/errors.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.