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.

Cline is a VS Code extension for agentic workflows. Point its OpenAI-compatible mode at routing.run so requests use your dashboard key and route/… model ids. Official references:

​
Setup

1

Get your API key

Create an API key at app.routing.run. Copy the key — it starts with rk_.
2

Open Cline settings

In VS Code, open the Cline extension from the sidebar. Click the gear icon to open settings.
3

Create a custom provider

In the model or API dropdown, choose OpenAI Compatible. Cline also documents Anthropic custom base URLs, but routing.run is a better fit in OpenAI Compatible mode because the Anthropic surface is still partial.
4

Configure connection

Set the following:
  • Base URL: https://api.routing.run/v1
  • API Key: full rk_… value from the dashboard API Keys page
  • Model ID: route/glm-5.1 (or any route/… your plan allows)

​
Manual configuration

If you want to fill Cline 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
Model IDroute/glm-5.1
Keep the route/ prefix on model ids. If Cline lets you save multiple providers, name this one routing.run so you can switch back quickly.

​
Important details

  • Cline’s key settings are API Provider, Base URL, API Key, and Model.
  • Prefer Cline’s OpenAI Compatible provider over Anthropic mode for routing.run.
  • Tool-heavy workflows depend on OpenAI-compatible tool-calling behavior, so test your chosen model before rolling it out across a team.
  • Live API checks showed that routing.run’s Anthropic-style endpoint can return an empty content string for some reasoning-oriented models, which is another reason to prefer OpenAI-compatible mode here.
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
Start with route/qwen3.6-plus for general coding work or route/glm-5.1-precision when you want stronger reasoning.