Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.routing.run/llms.txt

Use this file to discover all available pages before exploring further.

Kilo Code includes a VS Code extension and a separate CLI. This page covers only the extension. Use an OpenAI-compatible integration with routing.run’s base URL and route/… model IDs. UI details follow Kilo’s OpenAI-compatible integration docs. Official references:
For the terminal agent, see Kilo Code CLI.
Before you start, create an API key at app.routing.run under API Keys. Copy the full secret. It starts with rk_.

​
VS Code extension

1

Install Kilo Code

Install Kilo Code from the Visual Studio Marketplace, or search Kilo Code in the VS Code Extensions view (Ctrl+Shift+X / Cmd+Shift+X).
2

Open Kilo Code settings

Open Kilo Code from the activity bar, then open Settings and the Providers tab. Add or select an OpenAI-compatible provider.
3

Add routing.run as a custom provider

Set:
  • Provider name: routing.run if the UI offers a name field
  • Base URL (or API base): https://api.routing.run/v1 — no trailing slash
  • API Key: your full rk_… secret
  • Model: a route/… id your plan allows (for example route/glm-5.1)

​
Manual configuration

If you want to fill the Kilo Code extension settings manually, use these exact values:
FieldValue
Provider namerouting.run if the UI offers a name field
Provider typeOpenAI-compatible
Base URLhttps://api.routing.run/v1
API Keyrk_REPLACE_ME
Modelroute/glm-5.1
Keep the route/ prefix on model ids. If Kilo lets you save multiple providers, name this one routing.run so you can switch back without re-entering values.

​
Important details

  • Kilo’s current docs center the Providers tab and an OpenAI-compatible provider, not generic OpenAI env vars alone.
  • Kilo also documents shared JSONC config files at ~/.config/kilo/kilo.jsonc and project kilo.jsonc.
  • If you use config files, the important keys are model, provider.<provider_id>.options.baseURL, and provider.<provider_id>.options.apiKey.
Published model IDs are listed on the models page. Exact access depends on your plan tier and the dashboard; common picks:
ModelUse case
route/glm-5.1-precisionStrongest reasoning-first choice
route/qwen3.6-plusBest default starting point
route/minimax-m2.7-highspeedLong-context sessions
route/kimi-k2.5Agentic and tool-heavy flows
route/glm-5.1Faster GLM alternative
route/qwen3.5-plusQwen3.5 flagship