Developer Quickstart Guide

Base URL and Authentication

Connect your scripts to our API by setting the base URL to https://api.grokunhingedmode.com/v1 and passing your key in the Authorization header. You get one active key per account, which you receive immediately after signing up with Google or an email address. There is no phone number requirement, and your prompts never leave our servers for training purposes. You can generate a new key anytime, but it will replace the existing one. Keep your key secure in your environment variables to avoid accidental exposure in your codebase.

First Request

Send a standard chat completion request to generate text from our uncensored model. The endpoint accepts JSON payloads with your system prompt and user messages. Use the model ID uncensored to ensure you are hitting our dedicated server. You do not need to specify a version number, as we only host this single model. The response returns generated text in the content field of the first choice.

Copycurl https://api.grokunhingedmode.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check system status and report latency"}]
  }'

Python SDK Integration

Use the official OpenAI Python library to interact with our API with minimal code changes. You only need to update the base_url and api_key parameters in your client initialization. This approach works because our endpoints follow the standard OpenAI specification exactly. You can pass your existing prompts and receive responses without rewriting your entire application logic. This makes switching from other providers or testing our uncensored model very fast.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.grokunhingedmode.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node SDK Setup

Integrate our API into your Node.js applications by configuring the OpenAI npm package with our custom base URL. Set the apiKey to your unique key and point baseURL to our server. The model parameter should be set to uncensored for every request. This setup allows you to use familiar Node.js patterns for making asynchronous API calls. You can handle errors and process responses just like you would with any other OpenAI-compatible service.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.grokunhingedmode.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming Responses and Token Usage

Enable streaming by setting stream to true in your request body to receive tokens as they are generated. The API sends Server-Sent Events (SSE) updates, allowing you to display text in real time. The final chunk of the stream contains the total token usage for that request, so you can track your billing accurately. This is crucial for managing costs since we charge per token. Streaming reduces perceived latency for your end users significantly.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Limits, Errors, and Context Window

Your account has a strict limit of 300 requests per minute and a maximum of 8 concurrent requests. The context window supports 100,000 tokens for input and output combined, with a default max output of 2,048 tokens. If you exceed the rate limit, you will receive a 429 error. A 401 error means your key is invalid, while a 402 indicates you need to top up your prepaid credit. You can only pay with USDT or USDC, starting from $20. Errors do not consume your credit, so you can retry failed requests freely.