FreeInference

Getting Started:

  • Quick Start
    • Step 1: Get Your API Key
    • Step 2: Configure Your Agent
      • Kilo Code (Recommended)
      • Cursor
      • Claude Code
      • Roo Code / Cline
      • Continue
      • Aider
      • Other Agents (Windsurf, Twinny, CodeGPT, etc.)
    • Step 3: Choose a Model
    • Next Steps
    • Need Help?
  • IDE & Coding Agent Integrations
    • Claude Code
      • How it works
      • One-click setup (macOS / Linux)
      • Manual setup
      • Choosing and checking a model
      • Verify the endpoint
      • Gateway limitations
      • Troubleshooting
      • See also
    • Kilo Code
      • Configuration Steps
      • Notes
    • Cursor
      • Configuration Steps
    • Cline
      • Configuration Steps
    • Continue
      • Configuration Steps
    • Roo Code
      • Configuration Steps
    • Codeium / Windsurf
      • Configuration Steps
    • JetBrains AI Assistant
    • Generic OpenAI-Compatible Clients
      • Python (OpenAI SDK)
      • curl
      • Node.js (OpenAI SDK)
    • Codebase Indexing
      • Roo Code
      • Kilo Code
      • Continue
      • Alternative: Local Qdrant
      • Using the Embedding API Directly
    • Troubleshooting
      • Connection Issues
      • Model Not Found
      • Cursor-Specific Issues
      • Kilo Code / Roo Code Issues
    • Quick Reference
    • Need Help?
  • Cloud Agents
    • How it works
    • Connect GitHub
    • Run a task
    • Choosing an agent and model
    • What to delegate
    • Usage and budgets
    • Security
    • See also
  • Available Models
    • Model Overview
    • Embedding Model
    • Choosing a Model
    • Access and Retired IDs
    • Switching Models
  • API Headers Reference
    • Authentication
      • Authorization
      • X-API-Key
    • Request Behavior
      • X-Reasoning-Passthrough
      • X-Session-ID
      • X-Probe
      • X-Route-Pin
    • Anthropic API
      • Anthropic-Version
      • anthropic-beta
    • Tracing
      • X-Request-ID
    • Qdrant Proxy
      • api-key
    • Proxy Headers
    • Standard Headers
FreeInference
  • Search

© Copyright 2025-2026, Harvard System Lab.

Built with Sphinx using a theme provided by Read the Docs.