Use an uncensored model in Roo Code

Roo Code is an OpenAI-compatible coding agent for VS Code. Its OpenAI Compatible provider lets you point it at Obscurify.ai and run an uncensored model that won’t refuse. You get 200+ models through one key and an account number instead of an email.

Config verified against Roo Code’s docs on 2026-11-08 (Roo Code is a VS Code extension with no official CLI, so this was not run here). Obscurify.ai’s OpenAI-compatible API itself is tested in our Cline and OpenCode tutorials, which use the same endpoint.

Before you start

  • Roo Code, the VS Code extension from the marketplace.
  • An Obscurify.ai API key. Create an account — a random 16-digit number, no email. Add credit on the account page, then click Show API Key. The key starts with sk-obs1_ and can be fetched again from your account number. New accounts may get $1 of starter credit while this month’s promo budget lasts.

Add the provider

Open the Roo Code panel, then its settings. Under Providers:

  • API Provider: OpenAI Compatible
  • Base URL: https://obscurify.ai/v1
  • API Key: your sk-obs1_... key
  • Model: an id from the list below

Roo Code added native tool calling for OpenAI-compatible providers in 3.33, so pick a model that supports tools (all the ones below do) and enable it if your version offers the toggle.

Pick a model

From /v1/models (prices on the model list), keeping the full id:

  • Uncensored, needs Pro: z-ai/glm-5.3-flash-uncensored or deepseek/deepseek-v4.1-flash-uncensored.
  • Decensored, any funded account: pqhaz/deepseek-v4.1-flash-1017-heretic.

What it costs

Billed from your balance at each model’s price. Agent tasks use far more tokens than chat (about 20,000 tokens for small tasks in our tests). Paid models have no monthly token limit. See pricing.

If something fails

  • 402: no balance — add credit on the account page.
  • 403 model_not_on_plan: uncensored models need Pro; decensored models work on any funded account.
  • 404 model_not_found: check the id against /v1/models and keep its prefix.
  • 429: slow down, or you’ve used this month’s free-model tokens.

What stays private

Prompts and responses aren’t stored on Obscurify.ai’s servers; models with the ZDR tag run only on zero-data-retention routes. Providers see the prompt text (including files Roo Code sends) but not who sent it. See the privacy policy.

More agents: Obscurify.ai for agents.