Skip to main content

​
Documentation Index

Fetch the complete documentation index at: https://docs.llmrouter.app/llms.txt Use this file to discover all available models, tags, and features.

​
Cursor Integration

You can easily connect Cursor to LLM Router using the OpenAI-compatible API. This gives you access to intelligent routing, Skills, context optimization, Zero Data Retention, and more — all powered by your configured settings.
Note: Custom provider configuration is only supported in Cursor Pro and higher versions.

​
1. Install Cursor

Download and install the latest version of Cursor from the official website.

​
2. Add LLM Router as a Custom Model

  1. Open Cursor and navigate to Settings → Models.
  2. Click Add Custom Model (or Add OpenAI API Key).
  3. Configure the following:
    • Protocol: Select OpenAI
    • OpenAI API Key: Paste your LLM Router API key (sk_llmr_...)
    • Override OpenAI Base URL: Set it to https://api.llmrouter.app/v1
    • Model Name: Enter any supported model, for example:
      • anthropic/claude-opus-4.6
      • openai/gpt-5.4
      • google/gemini-3.1-pro
      • xai/grok-4.20
Routing behavior, tags, Skills, Zero Data Retention (ZDR), and other preferences are configured in the LLM Router Dashboard.
  • Log into your LLM Router Dashboard.
  • Go to your API keys section.
  • Set default routing rules, assign tags (e.g. coding, ui design, testing, copywriting), enable Skills, turn on ZDR, and define other optimizations.
  • These settings will automatically apply to all requests made with that API key when using Cursor.
This centralized approach ensures consistent behavior across all your tools and applications without needing to modify requests manually.

​
4. Save and Start Coding

After saving the model in Cursor, select your new LLM Router provider. You’re now ready to code with the full power of LLM Router:
  • Intelligent tag-based model routing
  • Automatic relevant Skill injection (enableAutoSearch)
  • Aggressive context pruning and optimization
  • Zero Data Retention for sensitive work
  • Significant cost savings
  • anthropic/claude-opus-4.6 — Best for complex reasoning and high-quality code
  • anthropic/claude-sonnet-4.6 — Excellent speed/quality balance
  • openai/gpt-5.4 — Strong general-purpose performance
  • google/gemini-3.1-pro — Great for multimodal and long-context tasks