NeverMetered
Get API key

Use NeverMetered with Copilot CLI

GitHub's terminal coding agent, using Copilot CLI's official Bring Your Own Key (BYOK) support.

OpenAI Chat
Model
qwen3.8-27b
128K context on the free plan65,536 max output tokens on the free planReplace YOUR_API_KEY with your key.
  1. 1

    Create an API key

    Create a key in API keys and name it after the tool, for example “Copilot CLI”. A dedicated key per tool lets you see its usage separately and give it its own parallel-stream cap. The key is shown once; the snippets below use YOUR_API_KEY where it goes.

  2. 2

    Install Copilot CLI

    Already have Copilot CLI? Skip this step. Open a terminal first: on macOS press ⌘ Space, type Terminal and press Return; on Windows open the Start menu, type PowerShell and press Enter. It needs an active GitHub Copilot subscription.

    curl -fsSL https://gh.io/copilot-install | bash
  3. 3

    Point Copilot CLI at the gateway

    Set these before starting copilot. The variable names are fixed by GitHub's BYOK support, not configurable.

    export COPILOT_PROVIDER_BASE_URL="https://api.nevermetered.com/v1"
export COPILOT_PROVIDER_API_KEY="YOUR_API_KEY"
export COPILOT_MODEL="qwen3.8-27b"
copilot
  4. 4

    Keep it for new terminals (optional)

    The command above only lasts for the current terminal. Save it once so every new terminal has it.

    # zsh (the macOS default)
echo 'export COPILOT_PROVIDER_BASE_URL="https://api.nevermetered.com/v1"' >> ~/.zshrc
echo 'export COPILOT_PROVIDER_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
echo 'export COPILOT_MODEL="qwen3.8-27b"' >> ~/.zshrc
# bash
echo 'export COPILOT_PROVIDER_BASE_URL="https://api.nevermetered.com/v1"' >> ~/.bashrc
echo 'export COPILOT_PROVIDER_API_KEY="YOUR_API_KEY"' >> ~/.bashrc
echo 'export COPILOT_MODEL="qwen3.8-27b"' >> ~/.bashrc
  5. 5

    Verify it works

    Start a session and send a short prompt. The request shows up in Requests within a few seconds, with its input, cached and output tokens.

    copilot
Tips
  • GitHub's BYOK support only covers models that support tool calling and streaming; every model this gateway serves qualifies.
  • It's built for OpenAI Chat Completions-compatible endpoints specifically (also how Ollama and vLLM plug in), which is exactly what this base URL serves.
  • COPILOT_PROVIDER_TYPE defaults to openai and doesn't need setting. GitHub recommends at least 128K context for BYOK models; your plan supports 131,072.

Troubleshooting

Copilot CLI can't reach the provider
COPILOT_PROVIDER_BASE_URL wasn't visible to the copilot process. Export it in the same shell (or persist it) and start a new session.
404 model_not_found
Use a model id exactly as GET /v1/models lists it, for example qwen3.8-27b. Plans can restrict which models a key may call.
400 context_length_exceeded
The conversation outgrew the 128K context window (input + output). Let the tool compact or start a fresh session, or get a larger window on your plan.
429 concurrency_limit_exceeded
All your parallel streams are busy and your queue allowance is full. Lower the tool's parallelism (subagents, batch size), or get more streams on your plan.
Answers stop mid-sentence
The response hit your plan's output cap of 65,536 tokens (finish reason length or max_tokens). Ask for shorter steps, or upgrade for a higher cap.
403 email_verification_required
Free requests need a verified email. Click the link in your verification email (you can resend it from the dashboard), or upgrade.
429 daily_quota_exceeded
You've used today's free requests; agents send one request per step, so they go quickly. The allowance resets at 00:00 UTC, and paid plans have no daily limit.
503 / 504 request_queue_timeout
The service stayed busy longer than the queue timeout and nothing was generated. Retry with backoff, and give the tool a generous request timeout.
503 service_unavailable
No GPU capacity is online at the moment. It's temporary and your setup is fine: retry in a little while, and check the status page.