Unrestricted Character AI API Documentation

Base URL and Authentication

The API key authenticates your requests. Use Continue with Google or email signup to generate one instantly. Set the base URL to https://api.unrestrictedcharacterai.com/v1 in your client configuration. This works with any OpenAI-compatible SDK.

Copycurl https://api.unrestrictedcharacterai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set the temperature to 0.7 for stable replies."}]
  }'

Chat Completions Endpoint

Send messages to POST /v1/chat/completions. The model ID is uncensored. It responds to lawful adult, fictional, or controversial topics without refusal. Text in, text out. No extra services clutter the request.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.unrestrictedcharacterai.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 Integration

Use the official Node SDK for seamless integration. Pass the base URL and key. The client handles the HTTP layer. You receive structured JSON responses. Error handling is standard. Check the status code.

Copyimport OpenAI from "openai";

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

Enable streaming by setting stream: true. You receive Server-Sent Events (SSE). Token usage appears in the last chunk. This reduces perceived latency for long outputs. The model generates text token by token.

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)

JSON Mode and Function Calling

Use response_format: {"type": "json_object"} for strict JSON. Function calling supports tools and tool_choice. Define schemas in your messages. The model adheres to the structure. Parse the output programmatically.

Limits and Errors

Rate limit is 300 requests per minute. Context window is 100,000 tokens. Error 401 means invalid key. Error 402 means no credit. Error 429 means rate limit exceeded. Max request body is 8 MB. Use these codes to debug quickly.