Uncensored chatgpt API Documentation

Authentication with your API key

The base URL for all requests is https://api.chatgptuncensored.cc/v1. Append your unique API key to the Authorization header as a Bearer token. Our system validates credentials instantly. If the key is missing or invalid, the API returns a 401 error. You receive your key immediately after signup via Google or email. No phone number is required. The key identifies your account for rate limiting and billing.

POST /v1/chat/completions

Send your prompt to the chat completions endpoint. This standard endpoint accepts a JSON body with messages and model parameters. Our API key ensures you access the uncensored model directly. You can adjust temperature and top_p to control creativity. The system processes your text and returns a completion. This works with any OpenAI-compatible client library.

Python SDK integration

Initialize the OpenAI client with your custom base URL. Set the API key and model ID to uncensored. Pass your messages array to the chat completions function. The client handles the JSON serialization automatically. You receive a response object with the generated text. This approach requires minimal code changes from your existing setup.

Node SDK setup

Configure the Node.js client with the same base URL structure. Use the uncensored model ID for all requests. The SDK manages the HTTP connections efficiently. You can integrate this into existing Node applications seamlessly. Error handling works as expected with standard HTTP status codes. The response contains the generated content and usage stats.

Streaming responses

Enable streaming by setting stream: true in your request. The API returns chunks via Server-Sent Events (SSE). Each chunk contains partial text or token usage data. This reduces perceived latency for long responses. You can display tokens as they arrive. The final chunk includes the total token count for billing.

Rate limits and constraints

Each API key allows 300 requests per minute. You can run 8 concurrent requests simultaneously. The request body must not exceed 8 MB. If you exceed the rate limit, the API returns a 429 error. Insufficient credit triggers a 402 error. Errors and refusals do not consume your token balance. The context window supports 100,000 tokens total. Max output is 16,000 tokens per request.

cURL

Copycurl https://api.chatgptuncensored.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of france"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatgptuncensored.cc/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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatgptuncensored.cc/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

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)