>_ cc-copilot-bridge

cc-copilot-bridge FAQ

Everything you need to know about legal status, costs, providers, and model selection.

Legal & Risk

Is cc-copilot-bridge legal to use?

Using copilot-api (the Copilot provider) may violate GitHub's Terms of Service. The tool itself is MIT licensed, but how you use it matters.

For risk-free usage, use the Anthropic Direct (ccd) or Ollama (cco) providers — both operate within their respective Terms of Service.

Pricing & Costs

How much does cc-copilot-bridge cost?

Depends on the provider:

  • Copilot: uses your existing subscription quota (GitHub Copilot Pro+ at $10/month)
  • Anthropic Direct: pay-per-token ($0.015–$75/1M tokens depending on model)
  • Ollama: free (local compute only)
Why is GPT-4.1 free on Copilot?

GitHub assigns a 0x multiplier to GPT-4.1, GPT-4o, and GPT-5-mini on paid plans. This means they don't consume your premium request quota.

Use them for routine tasks (boilerplate, simple refactors) to preserve your premium quota for Claude Opus or other higher-cost models.

Getting Started

What is copilot-api?

copilot-api is a community project that reverse-engineers GitHub Copilot's API. It's the bridge that makes the Copilot provider possible.

cc-copilot-bridge is a wrapper that makes it easy to use with Claude Code CLI — managing the proxy lifecycle, aliases, and model routing automatically.

How do I start copilot-api?

Terminal 1: Keep this running

copilot-api start

Terminal 2: Use Copilot mode

ccc  # or ccc-opus, ccc-gpt, etc.

Alternative: For Codex models (gpt-5.2-codex), use the unified fork:

ccunified  # or ~/path/to/cc-copilot-bridge/scripts/launch-unified-fork.sh

💡 Tip: Check if copilot-api is running: ccs (shows status of all providers)

Does Ollama work offline?

Yes, 100%. Ollama runs entirely on your machine with no internet required. Perfect for:

  • Proprietary code you can't send to external APIs
  • Air-gapped environments
  • Privacy-first workflows

Use alias cco to start Claude Code with your local Ollama instance.

Providers & Models

Which models are available?

Anthropic Direct: Claude Opus 4.5, Sonnet 4.5, Haiku 4.5

Copilot: Claude family, GPT-4.1/5, Gemini 2.5 Pro

Ollama (Local):

  • Devstral-small-2 (68% SWE-bench — best agentic coding)
  • Granite4 (62%, excellent long context)
  • Qwen3-coder (69.6%, needs template config)
  • Any model you install via ollama pull
Why Devstral over Qwen3-coder for Ollama?

Qwen3-coder has 1.6% higher SWE-bench (69.6% vs 68%), but Devstral is more reliable in practice:

  • Architecture: Devstral = native agentic design vs Qwen3 = post-training bolt-on
  • Practice: Devstral = "best agentic" confirmed vs Qwen3 = "needs template work"
  • Precedent: High benchmarks ≠ reliability (Llama3.1:8b = 68% HumanEval but 15% SWE-bench)

SWE-bench measures real GitHub issue resolution with tool calling, not just code completion. Devstral wins on practical reliability.