copilot-api

A proxy server that turns a GitHub Copilot subscription into fully compatible OpenAI and Anthropic API endpoints. Use Claude Code, Codex CLI, and any tool that speaks the API -- all through the Copilot plan you already pay for, no separate API keys required.

Table of Contents

• Key Features
• Quick Start
  • Claude Code
  • Codex CLI
  • Web Search
• API Endpoints
• CLI Reference
  • Commands
  • start Flags
• Telemetry
• Closed Source
• Notices
• Attribution
• License

Key Features

| Feature | Description | |:--|:--| | Full Claude Code support | All Claude models, streaming, extended thinking, and the complete 1M token context window | | Full Codex CLI support | Complete OpenAI Responses API implementation purpose-built for Codex CLI | | Web search | Optional Tavily-powered web search available to both Claude Code and Codex sessions | | Dual API compatibility | OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses APIs side by side | | Zero configuration | Single command to start -- authenticates via GitHub device-code OAuth |

Quick Start

Prerequisites: Node.js 20+ (or Bun) and an active GitHub Copilot subscription.

Claude Code

Start the proxy with Claude Code mode:

npx copilot-api-node20@latest start --claude-code

On first run, you authenticate via GitHub device-code OAuth. Once authenticated, the proxy starts on http://localhost:4141 and prints a ready-to-paste command. In another terminal:

ANTHROPIC_BASE_URL=http://localhost:4141 claude

To skip the interactive model picker, specify models upfront:

npx copilot-api-node20@latest start \
  --claude-code \
  --model claude-opus-4.6-1m \
  --small-model claude-haiku-4.5

Codex CLI

Start the proxy with Codex mode:

npx copilot-api-node20@latest start --codex --model gpt-5.3-codex

Configure ~/.codex/config.toml:

model = "gpt-5.3-codex"
model_provider = "local"

[model_providers.local]
name = "Local Server"
base_url = "http://localhost:4141/v1"
env_key = "OPENAI_API_KEY"

Then run:

OPENAI_API_KEY=dummy codex

Web Search

Provide a Tavily API key to enable web search tool calls in both Claude Code and Codex sessions:

npx copilot-api-node20@latest start --claude-code --tavily-api-key <key>

Alternatively, set TAVILY_API_KEY as an environment variable. The proxy operates normally when no key is provided -- web search is simply unavailable.

API Endpoints

All endpoints are served at http://localhost:4141 by default.

| Method | Path | Compatibility | |:--|:--|:--| | POST | /v1/chat/completions | OpenAI Chat Completions | | POST | /v1/responses | OpenAI Responses API | | POST | /v1/messages | Anthropic Messages | | POST | /v1/messages/count_tokens | Anthropic Token Counting | | POST | /v1/embeddings | OpenAI Embeddings | | GET | /v1/models | OpenAI Models | All OpenAI-compatible routes are also available without the /v1/ prefix.

CLI Reference

Commands

| Command | Description | |:--|:--| | copilot-api start | Start the proxy server | | copilot-api auth | Authenticate with GitHub | | copilot-api check-usage | Display Copilot usage quota | | copilot-api debug | Print diagnostic information |

start Flags

--claude-code and --codex are mutually exclusive.

| Flag | Alias | Default | Description | |:--|:--|:--|:--| | --port | -p | 4141 | Port to listen on | | --claude-code | -c | | Enable Claude Code compatibility mode | | --codex | | | Enable Codex CLI compatibility mode | | --model | -m | | Primary model to use | | --small-model | -s | | Lightweight model for fast tasks (Claude Code) | | --rate-limit | -r | | Minimum seconds between requests | | --timeout | -t | 600000 | Request timeout in ms (default 10 min) | | --account-type | -a | individual | individual, business, or enterprise | | --github-token | -g | | Provide a GitHub token directly (skips OAuth) | | --show-token | | | Display tokens on fetch and refresh | | --tavily-api-key | | | Tavily API key for web search | | --verbose | -v | | Enable debug-level logging |

Telemetry

This tool collects anonymous usage telemetry via OpenTelemetry. Only operational metrics are collected -- request counts, latency, model usage, and error rates. No prompts, completions, or personal information is ever collected.

By using copilot-api, you agree to this telemetry data collection.

Closed Source

The source code is not publicly available.

This fork represents ~9 months of sustained engineering work -- bug fixes, new features, and hardening that go well beyond the original project. Keeping it closed-source protects that investment and ensures a single, well-maintained distribution.

The original open-source project is available at ericc-ch/copilot-api.

Notices

This project relies on reverse-engineered, undocumented GitHub APIs. It is not affiliated with or endorsed by GitHub, Microsoft, Anthropic, or OpenAI and may break without notice.

• Use --rate-limit to throttle requests and reduce abuse-detection risk.
• Review the GitHub Acceptable Use Policies and GitHub Copilot Terms before use.
• This software is provided as-is with no warranty.

Attribution

Originally created by Erick Christian -- ericc-ch/copilot-api. His work built the foundation: authentication flow, API translation layer, and streaming implementation.

This fork has diverged significantly over ~9 months with extensive bug fixes and major new features -- Anthropic Messages API, OpenAI Responses API, Claude Code mode, Codex CLI support, web search integration, usage telemetry, and more. It is maintained as a separate project by johnib.

License

MIT