Quick Documentation: Integrate the Uncensored Model

Base URL and Authentication Setup

To get started, you need an API key. Register on the account creation page with just your email and a password; the key is displayed instantly. No card is required for the $0.50 free trial credit. Set the OPENAI_API_KEY environment variable with your unique key. The base URL for this service is https://api.apiiasincensura.com/v1. This endpoint is natively compatible with the OpenAI client ecosystem, facilitating the integration of your uncensored llm api into existing applications without complex adapters.

Main endpoint: POST /v1/chat/completions

The main endpoint is POST /v1/chat/completions. Here you send your conversation and receive generated text. The model is invoked with the ID uncensored. This service is a strictly text-based api ia: it does not support embeddings, images, audio, or video. The request must follow the standard chat format. If you need to test connectivity, use GET /v1/models to verify that the service responds correctly before sending the payload.

Copiarcurl https://api.apiiasincensura.com/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 Support (SSE)

The chat completions endpoint supports real-time responses via Server-Sent Events (SSE). By setting stream: true, you will receive a stream of text fragments instead of a complete response all at once. This is ideal for user interfaces that display generation letter by letter. The model responds immediately without waiting for the full context to finish, keeping latency low even for long responses within the 100,000 token context window.

Copiarstream = 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)

Tools and Function Calling

The uncensored ai api supports native tool/function calling. You can define functions in the request body and the model will return the necessary JSON arguments to execute them. This allows building agents or applications that interact with external systems. The model is optimized to follow JSON structure instructions without refusing to generate code or technical data due to content restrictions. Make sure to parse the model response to extract the tool arguments.

Copiarfrom openai import OpenAI

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

Python/JS Code Example

Integration is straightforward using the official SDKs. In Python, initialize the client pointing to our base URL. In JavaScript, the configuration is similar. Remember that there is only one model available: uncensored. There is no routing or model selection. The code must handle model responses and manage the end of the stream if you use streaming. The simplicity of the unrestricted ai lies in the fact that you only need to handle standard input and output text.

Copiarimport OpenAI from "openai";

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

Rate Limits and Request Body

Respect the technical limits to avoid interruptions. The maximum quota is 300 requests per minute per API key. The request body cannot exceed 8 MB. If you exceed these limits, the API returns a 429 Too Many Requests status code. If your prepaid credit balance runs out, you will receive a 402 Payment Required code. Credit never expires, so you can top up whenever you want without penalties. The context window is 100,000 tokens combined between prompt and completion.