rk_ key, and a route/… model id.
Setup
Get your API key
Create an API key at app.routing.run. Copy the key — it starts with
rk_.Open Roo Code settings
In VS Code, open the Roo Code extension from the sidebar. Click the gear icon to open integration settings.
Create a custom provider
In the model or API dropdown, choose OpenAI Compatible or the custom provider flow if your version separates them. Name the provider
routing.run if the UI offers a provider name field.Manual configuration
If you want to fill Roo Code settings manually, use these exact values:| Field | Value |
|---|---|
| Provider name | routing.run if the UI offers a name field |
| Provider type | OpenAI Compatible |
| Base URL | https://api.routing.run/v1 |
| API Key | rk_REPLACE_ME |
| Model ID | route/glm-5.1 |
route/ prefix on model ids. If Roo Code lets you save multiple providers, name this one routing.run so you can switch back quickly.
Recommended models
Plan tier and access are authoritative on GEThttps://api.routing.run/v1/models with your rk_ key. The full list is on the models page; common picks:
| Model | Use case |
|---|---|
route/deepseek-v3.2 | General-purpose chat (matches most doc examples) |
route/glm-5.1 | Reasoning and coding |
route/minimax-m2.7 | Long-context sessions |
route/kimi-k2.5 | Agentic and tool-heavy flows |
route/qwen3.6-plus-preview | Qwen3.6-class preview |
route/qwen3.5-plus | Qwen3.5 flagship |