Unsensored AI API Documentation

Authentication and base URLs

Use the official OpenAI SDKs with a custom base URL. Your API key authenticates every request.

Base URL: https://api.unsensoredai.com/v1

Model ID: uncensored

Copycurl https://api.unsensoredai.com/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"}]
  }'

Chat completions endpoint

Send messages via POST /v1/chat/completions. The model returns text without content filters.

Context window: 100,000 tokens total. Max output: 16,000 tokens.

Copyfrom openai import OpenAI

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

Streaming responses

Enable streaming for real-time token delivery. The final chunk contains usage data.

Useful for low-latency interfaces.

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)

Function calling and tools

Supports tool definitions and automatic function calling. Define tools in the request body.

The model selects tools based on context.

Copyimport OpenAI from "openai";

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

JSON mode and parameters

Force structured output with response_format: {"type": "json_object"}. Control temperature, top_p, and stop sequences.

Set seed for reproducibility.

Rate limits and quotas

300 requests per minute per key. 8 concurrent requests allowed.

8 MB request body limit. Errors are free. Credits expire only if unpaid.