API Documentation for Uncensored Models

Authentication and Base URL

Start by generating your key via the dashboard. Use the official base URL and set the X-Api-Key header. We do not require a phone number for signup, and your key is shown immediately.

Copycurl https://api.isgrokaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five terminal commands for log analysis"}]
  }'

Each account supports one active key. If you generate a new one, the old key is replaced instantly. This keeps your integration simple and secure without managing multiple credentials.

Chat Completions Endpoint

Send a POST request to the chat completions endpoint. The model ID is always uncensored. We only serve this single open-weight model, optimized for freeform reasoning.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.isgrokaiuncensored.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)

You do not need to switch SDKs. Our API is fully OpenAI-compatible. Just update your base URL and API key in your client configuration.

Streaming Responses and Usage

Enable streaming by setting stream: true. You receive Server-Sent Events (SSE) tokens. The final chunk contains the full token usage statistics.

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)

This approach is ideal for real-time UI updates. You do not wait for the entire response to arrive before displaying text. Errors during streaming are handled gracefully by the client.

Function Calling and JSON Mode

Define tools in your request body for function calling. You can also force JSON output using response_format set to json_object.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.isgrokaiuncensored.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);

These features work exactly as documented in the OpenAI spec. Your existing parsing logic remains valid. We do not add custom fields that break standard clients.

Parameters: Temperature and Top P

Control randomness with temperature and top_p. You can also set seed for reproducible outputs. These parameters are standard across OpenAI-compatible APIs.

Copycurl https://api.isgrokaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five terminal commands for log analysis"}]
  }'

Adjust these values to tune creativity. Higher temperatures yield more diverse responses. Lower values make outputs more deterministic. We do not hide these controls behind a premium tier.

Limits, Errors, and Context Window

The context window is 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request. You are limited to 300 requests per minute.

Copycurl https://api.isgrokaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five terminal commands for log analysis"}]
  }'

Errors like 401 indicate an invalid key. 402 means you have no credit. 429 signals a rate limit. These are standard HTTP codes. We do not use custom error formats.