API Documentation for uncensored ai chat

Authentication and Base URL

The base URL is https://api.aichatunrestricted.com/v1. Pass your API key in the Authorization header. Payments use crypto only. Use USDT (TRC20) or USDC (Base) to top up. Credit never expires.

POST /v1/chat/completions

Send text to the uncensored model. The API returns text without content refusals for lawful adult use.

• Max context: 100,000 tokens.
• Max output: 16,000 tokens.

Example request:

Copycurl https://api.aichatunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the steps to install pip on ubuntu"}]
  }'

GET /v1/models

Verify available models. The response lists the uncensored model. Use this endpoint to confirm connectivity.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aichatunrestricted.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 Example

Use the Node SDK with the custom base URL. Set the API key and model ID. This ensures compatibility with existing client code.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aichatunrestricted.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 and SSE

Enable streaming by setting stream: true. You receive Server-Sent Events. Token usage appears in the final chunk. This reduces perceived latency for long responses.

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 and Errors

Rate limit is 300 requests per minute. Concurrency limit is 8 simultaneous requests. Request body max is 8 MB. Errors include 401 for invalid keys and 402 for no credit. The context window is 100,000 tokens.