NeverMetered
Get API key

Use NeverMetered with Oh My Pi

A batteries-included fork of Pi (the `omp` command), configured with a custom provider in models.yml.

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 “Oh My Pi”. 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 Oh My Pi

    Already have Oh My Pi? 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. Its command is omp.

    curl -fsSL https://omp.sh/install | sh
  3. 3

    Add the provider

    Save this as models.yml in Oh My Pi's config folder (create the file if it doesn't exist, or add the provider to the one you have). Oh My Pi reads the apiKey value as the name of an environment variable.

    ~/.omp/agent/models.yml
    providers:
  nevermetered:
    baseUrl: https://api.nevermetered.com/v1
    api: openai-completions
    apiKey: NEVERMETERED_API_KEY
    auth: apiKey
    models:
      - id: qwen3.8-27b
        name: qwen3.8-27b
        contextWindow: 131072
        maxTokens: 65536
        reasoning: true
        thinking:
          mode: effort
          efforts: [low, medium, high, xhigh]
          defaultLevel: medium
  4. 4

    Export your key

    export NEVERMETERED_API_KEY="YOUR_API_KEY"
  5. 5

    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 NEVERMETERED_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
# bash
echo 'export NEVERMETERED_API_KEY="YOUR_API_KEY"' >> ~/.bashrc
  6. 6

    Check that Oh My Pi sees the model

    List the models it found for the provider. You should see qwen3.8-27b.

    omp models nevermetered
  7. 7

    Start Oh My Pi with the model

    Inside a session, /model lets you assign it to the default role so you don't need the flag next time.

    omp --model nevermetered/qwen3.8-27b
  8. 8

    Verify it works

    Run a single prompt and exit. The request shows up in Requests within a few seconds, with its input, cached and output tokens.

    omp --model nevermetered/qwen3.8-27b -p "Reply with the word ready"
Tips
  • contextWindow and maxTokens tell Oh My Pi the model's real limits, so it compacts long sessions before the engine rejects them.
  • Subagents and parallel tool runs each use one of your parallel streams.
  • Thinking counts against the output limit. Change the thinking level inside Oh My Pi to control how much the model thinks: lower it for quick edits and keep high or above for hard problems.

Troubleshooting

Oh My Pi stops partway through a task or replies with nothing
The model probably spent its whole output allowance thinking, leaving nothing for the answer. Lower the thinking level and resend, and check that maxTokens isn't below your plan's output cap. Don't switch the model's thinking block to mode: budget: this API rejects token-budget fields with a 400 error.
401 invalid API key
If NEVERMETERED_API_KEY isn't set in the terminal you started omp from, Oh My Pi sends the text NEVERMETERED_API_KEY as the key. Export the variable there, or open a new terminal after saving it to your profile.
omp models doesn't list the provider
Check the file path and that the providers: block is indented with spaces, not tabs. A provider needs baseUrl, api, apiKey and a non-empty models list.
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.