Docs
One key, three request formats, 7 models that do not refuse the task. Start with the quickstart, or go straight to the page for your agent.
- OpenAI format base URL
https://uncensoredopencode.com/v1- Anthropic format base URL
https://uncensoredopencode.com- Key
sk-nc-...from the dashboard- Default model
glm-5.3-flash-uncensored
Get started
Quickstart: first requestMake a key, send one request, read the reply. Three minutes, and everything after this page builds on it.Quickstart: opencodeOne provider block in opencode.json. opencode then lists the models under Uncensored Opencode in /models.Quickstart: Claude CodeClaude Code speaks the Anthropic messages format, which this API serves. Three environment variables and it runs on a model from this line.Quickstart: CodexCodex reads extra model providers from its config file. Add this one and set the key in your shell.Quickstart: Hermes AgentHermes Agent takes any OpenAI-compatible endpoint as a custom provider.
The API
FormatsThe same models answer in three request formats. Use whichever your tool already speaks; the key and the billing are the same.Models7 models. Every id below is exactly what goes in the model field.Tool callingEvery model on the line calls tools. This is what an agent harness relies on, so it is the part worth knowing exactly.
Spend
KeysOne key per app, agent or person, each with its own name and its own cap if you want one.Spend capsA cap is a ceiling in dollars on one key. An agent that loops stops at the figure you chose, not at your whole balance.BillingPrepaid credit, spent by the token at each model's listed price. No plan and no subscription.