Use an uncensored model in Kilo Code

Kilo Code is an OpenAI-compatible coding agent, in VS Code and in the terminal. You can add Obscurify.ai as a custom provider and run an uncensored model that won’t refuse security research or blunt output. You get 200+ models through one key and an account number instead of an email.

Tested on 2026-11-08 with the Kilo Code CLI 7.8.27 against the live API, including an agent run that wrote a file through a tool. The VS Code extension uses the same OpenAI-compatible provider fields, noted below.

Before you start

  • Kilo Code. The VS Code extension, or the CLI: npm install -g @kilocode/cli.
  • 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.

Pick a model

From /v1/models (prices on the model list), keeping the full id. All do tool calling:

  • 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 (used in the test below).

CLI setup (tested)

The Kilo CLI reads a provider config. Put this in ~/.config/kilo/kilo.json:

{
  "$schema": "https://kilocode.ai/config.json",
  "provider": {
    "obscurify": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Obscurify.ai",
      "options": {
        "baseURL": "https://obscurify.ai/v1",
        "apiKey": "sk-obs1_..."
      },
      "models": {
        "pqhaz/deepseek-v4.1-flash-1017-heretic": { "name": "DeepSeek Heretic (Obscurify)" }
      }
    }
  }
}

Then run a task — the model id is provider/model:

kilo run -m "obscurify/pqhaz/deepseek-v4.1-flash-1017-heretic" \
  "Create a file named hello.txt containing exactly: obscurify works. Then reply DONE."

kilo config check confirms the config, and kilo models | grep obscurify lists your models.

VS Code extension setup

In the Kilo Code panel, open Settings → Providers and choose OpenAI Compatible. Set the Base URL to https://obscurify.ai/v1, paste your sk-obs1_... API key, and enter the Model ID (for example pqhaz/deepseek-v4.1-flash-1017-heretic, or an uncensored id on Pro). Pick a model that supports tool calling, or the agent can’t act.

What it costs

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

If something fails

  • 402: no balance — add credit.
  • 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 your agent sends) but not who sent it. See the privacy policy.

More agents: Obscurify.ai for agents.