Use an uncensored model in OpenCode

OpenCode lets you add any OpenAI-compatible provider, so you can point it at Obscurify.ai and code with an uncensored model that won’t refuse. You get 200+ models through one key, and an account that’s a 16-digit number instead of an email.

Tested on 2026-11-08 with OpenCode 1.19.5 against the live API, including an agent run that wrote a file through a tool.

Before you start

  • OpenCode: npm install -g opencode-ai (or the install script on opencode.ai).
  • 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.

Put the key in your environment:

export OBSCURIFY_API_KEY="sk-obs1_..."

Add the provider

OpenCode reads opencode.json from your project (or ~/.config/opencode/). Add Obscurify.ai as an OpenAI-compatible provider:

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

Pick a model

Add any id from /v1/models to the models map, keeping its prefix. All of these 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 below).

Try it

The model ref is provider/model:

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

First run downloads the @ai-sdk/openai-compatible package, so it can take a couple of minutes once; after that it’s fast.

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 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 your agent sends) but not who sent it. See the privacy policy.

More agents: Obscurify.ai for agents.