Integrate Uncensored AI Models in Minutes

Base URL & Authentication

Our API follows the OpenAI standard, requiring only a base URL adjustment and an API key. The base URL is https://api.uncensoredaimodels.cc/v1. You receive a single active API key upon signup. Include it in the Authorization header as a Bearer token. If the key is invalid, the API returns a 401 error. If you lack sufficient credit, you receive a 402 error. This design allows you to swap our service into existing OpenAI clients by updating just two configuration values.

Chat Completions Endpoint

Send text to the model using the POST /v1/chat/completions endpoint. The model identifier is uncensored. Requests must stay within an 8 MB body limit and a 100,000-token context window. The model returns generated text without standard content refusals for lawful adult topics. Use this endpoint for direct text generation tasks.

Copycurl https://api.uncensoredaimodels.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Streaming Responses (SSE)

Enable real-time token delivery by setting stream: true. The API returns Server-Sent Events (SSE), allowing your application to process tokens as they generate. Token usage statistics appear only in the final chunk of the stream. This approach reduces perceived latency for users waiting for long-form content.

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)

Python SDK Integration

Use the official OpenAI Python library to integrate quickly. Set the base_url to our endpoint and provide your API key. The client handles serialization and error parsing automatically. This method is ideal for backend services or data processing scripts that require structured uncensored text output.

Copyfrom openai import OpenAI

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

For JavaScript environments, the OpenAI Node SDK works with our endpoint. Initialize the client with your base URL and key. This integration supports both synchronous and asynchronous requests, fitting well into Express servers or serverless functions. Ensure your environment supports the required Node version for the SDK.

Copyimport OpenAI from "openai";

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

Model Parameters & Limits

Control generation behavior using parameters like temperature, top_p, and seed. You can enforce JSON output via response_format or define tools for function calling. The API enforces a hard limit of 300 requests per minute and 8 concurrent requests per key. If you exceed these limits, the API returns a 429 error. Output is capped at 32,000 tokens per request.