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.

The @kilocode/cli runs the Kilo Code agent in your terminal. This page covers only the CLI; for the VS Code extension, see Kilo Code (VS Code). The CLI speaks OpenAI-compatible APIs: point it at routing.run’s base URL and use route/… model IDs. Official references:
For the VS Code extension, see Kilo Code (VS Code).
Before you start, create an API key at app.routing.run under API Keys. Copy the full secret. It starts with rk_.

​
CLI

1

Install the CLI

Install the official package globally with bun:
bun install -g @kilocode/cli
You can also run it once without installing:
bunx @kilocode/cli kilo --help
2

Configure the provider

Kilo documents both environment variables and JSONC config. For a durable setup, configure an OpenAI-compatible provider with routing.run as the base URL, then keep the API key in your shell environment.
3

Run Kilo Code

Start the CLI with kilo. Use kilo models or your usual flow to pick a model; use IDs with the route/ prefix (for example route/glm-5.1).

​
CLI connection prompt

The Kilo CLI supports OpenAI-compatible env vars and shared JSONC config. Paste this when onboarding yourself or a teammate. It includes the fastest env-based flow.

Kilo Code CLI — connect to routing.run

​
Manual configuration

If you want to configure Kilo Code CLI manually instead of using the prompt above, export these exact values before you run kilo: 
export ROUTING_RUN_API_KEY='rk_REPLACE_ME'
export OPENAI_API_KEY="$ROUTING_RUN_API_KEY"
export OPENAI_BASE_URL="https://api.routing.run/v1"
If you keep multiple CLI backends locally, save these exports in a shell wrapper, env file, or named Kilo config called routing.run so switching providers is simpler. Use a model id with the route/ prefix, for example route/glm-5.1.
Kilo also documents config files at ~/.config/kilo/kilo.jsonc and project kilo.jsonc. The important config 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