Use NeverMetered with Cline

Autonomous coding agent for VS Code. The same steps work for Roo Code and Kilo Code.

OpenAI Chat

Model

qwen3.8-27b

8,192 max output tokens on the free planReplace YOUR_API_KEY with your key.

1
Create an API key
Create a key in API keys and name it after the tool, for example “Cline”. 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.

Choose the OpenAI Compatible provider

Open Cline's settings (the gear icon in the Cline panel) and fill in:

API Provider:  OpenAI Compatible
Base URL:      https://api.nevermetered.com/v1
API Key:       YOUR_API_KEY
Model ID:      qwen3.8-27b

3
Set the model limits
Under Model Configuration, match the engine so Cline trims context before the request is rejected:
```
Max Output Tokens:    8192
```
4
Verify it works
Start a new task and send a short message. The request shows up in Requests within a few seconds, with its input, cached and output tokens.

Tips

Roo Code and Kilo Code are Cline forks: pick OpenAI Compatible there and use the same values.
The key is stored in VS Code's secret storage, not your settings file, so it won't end up in a repository.

Cline reports the context window is exceeded: Set Context Window Size to the model's real context window so Cline condenses the conversation earlier.
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.
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 8,192 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.