Guide
Use an uncensored model in Zed
Zed connects to unrestricted.sh through its OpenAI-compatible provider, with a few lines of config. You get Qwen3.8 27B Uncensored, a model for coding and chat with 262K context, at $1.00 per million input tokens.
Get an API key
Sign up, then add credit: API keys work after your first top-up of $5 or more. A first top-up of $10 or more adds $5 of bonus credit.
Connect Zed
Merge this into ~/.config/zed/settings.json. Then open Agent Settings (agent: open settings), find unrestricted.sh under LLM Providers and paste your API key; Zed keeps it in the system keychain. Checked against Zed's docs.
{
"language_models": {
"openai_compatible": {
"unrestricted.sh": {
"api_url": "https://api.unrestricted.sh/v1",
"available_models": [
{
"name": "qwen3.8-27b-uncensored",
"display_name": "Qwen3.8 27B Uncensored",
"max_tokens": 262144,
"max_output_tokens": 32768
}
]
}
}
}
}Pick the model
Pick unrestricted.sh Qwen3.8 27B Uncensored from the model menu in the Agent panel.
If something goes wrong
- 401 invalid_api_key
- Missing or revoked API key.
- 402 insufficient_funds
- Out of funds.
- 403 api_locked
- Add funds once to unlock API keys.
- 429 concurrent_request_limit
- Too many requests running on this account.
Every error the API returns is listed in the API reference.
What a session costs
Cached input: when your tool resends the start of a conversation, those tokens cost $0.10 per million instead of $1.00. Cached-input pricing applies to the API and coding tools; messages in the web chat pay the full input price.
A coding-agent turn with 60,000 tokens in, 55,000 of them cached, 1,500 out costs $0.015. The pricing page has every price and more examples.