NeverMetered
Get API key

Use NeverMetered with Aider

AI pair programming in your terminal, through Aider's OpenAI-compatible 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 “Aider”. 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 Aider

    Already have Aider? 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.

    curl -LsSf https://aider.chat/install.sh | sh
  3. 3

    Set the endpoint and start Aider

    The openai/ prefix tells Aider to use the OpenAI-compatible endpoint from OPENAI_API_BASE.

    export OPENAI_API_BASE="https://api.nevermetered.com/v1"
export OPENAI_API_KEY="YOUR_API_KEY"
aider --model openai/qwen3.8-27b
  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 OPENAI_API_BASE="https://api.nevermetered.com/v1"' >> ~/.zshrc
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
# bash
echo 'export OPENAI_API_BASE="https://api.nevermetered.com/v1"' >> ~/.bashrc
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bashrc
  5. 5

    Tell Aider the model's limits (optional)

    Aider doesn't know this model's context window and warns about it. Save this next to your repository (or in your home directory) to fix the warning and the cost display. Tokens aren't billed, so the costs are zero.

    .aider.model.metadata.json
    {
  "openai/qwen3.8-27b": {
    "max_input_tokens": 131072,
    "max_output_tokens": 65536,
    "input_cost_per_token": 0,
    "output_cost_per_token": 0,
    "litellm_provider": "openai",
    "mode": "chat"
  }
}
  6. 6

    Verify it works

    --message runs a single prompt and exits. The request shows up in Requests within a few seconds, with its input, cached and output tokens.

    aider --model openai/qwen3.8-27b --message "Reply with the word ready"
Tips
  • OPENAI_API_BASE and OPENAI_API_KEY affect every OpenAI-compatible tool in that shell. Set them per project (for example in a .env file Aider loads) if you also use OpenAI directly.

Troubleshooting

Aider warns about an unknown context window
Harmless, but add .aider.model.metadata.json with max_input_tokens to silence it and let Aider size the chat history correctly.
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.