Uncensored API Quickstart

Authentication

Authenticate requests with a bearer token passed in the Authorization header. Your API key is visible immediately after signup on the Get API key page. We support both Google single sign-on and traditional email password registration, ensuring you can start without phone number verification. The key grants access to the single uncensored model hosted on our infrastructure. Keep your credentials secure, as they represent your prepaid credit balance.

• Sign up via Google or email.
• Copy the generated API key.
• Include it in every request header.

Chat Completions Endpoint

Send text completions to the POST /v1/chat/completions endpoint. This standard interface accepts a list of messages and returns a generated response. You must specify the model identifier as uncensored to access the tuned large language model. The base URL is https://api.iatextesanscensure.com/v1. Use the official OpenAI SDKs by configuring this base URL and your API key. The endpoint handles simple text generation without requiring complex routing logic.

• Target the chat completions route.
• Set the model to uncensored.
• Pass your messages in the body.

Copycurl https://api.iatextesanscensure.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?"}]
  }'

Python SDK Integration

Use the official openai Python library to interact with the API. Configure the client with your specific base URL and API key. This approach allows you to leverage existing code patterns familiar to most developers. The library handles serialization and retries automatically. You can adjust parameters like temperature or top-p to control the output style. This method is ideal for backend services or data processing scripts.

• Install the openai package.
• Initialize the client with your credentials.
• Call the chat completions function.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.iatextesanscensure.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

Integrate the API into your JavaScript or TypeScript applications using the Node SDK. Similar to Python, you must override the default base URL to point to our servers. This allows you to use familiar methods for sending prompts and receiving responses. The SDK manages the request lifecycle and error handling. You can easily embed the API into web servers, bots, or automated workflows. Ensure you handle the response data according to your application logic.

• Install the node package.
• Configure the base URL.
• Execute the chat request.

Copyimport OpenAI from "openai";

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

Enable streaming by setting the stream parameter to true. The API returns a sequence of Server-Sent Events (SSE) instead of a single complete response. This reduces perceived latency by delivering tokens as they are generated. Each chunk contains partial data, and the final chunk includes the total token usage statistics. This feature is essential for real-time chat interfaces or interactive applications. Monitor the stream for completion or errors.

• Set stream: true.
• Listen for delta events.
• Handle the final usage chunk.

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 & Errors

Our API enforces strict limits to ensure stability for all users. You are allowed 300 requests per minute per key and 8 concurrent requests. The maximum context window is 100,000 tokens, including both prompt and completion. If you exceed these limits, you will receive specific HTTP error codes. A 401 error indicates an invalid or missing API key. A 402 error means your prepaid credit is exhausted. A 429 error signals that you have hit the rate limit. Requests that fail due to these limits do not consume your credit. Errors and refusals are free. Prepaid credit never expires, but mistakes like double charges are fixed via the Support page. We do not offer SLAs, certifications, or model routing. The model refuses sexual content involving minors. Crypto payments only. No fine-tuning. No embeddings. No image generation. No audio. No video. No search. No moderation. No team size. No founding year. No benchmarks. No named customers. No on-prem. No HIPAA. No SOC2. No ISO. No unlimited tier. No chat app. Just API. Uncensored IA. Unscored IA. API IA. API IA contenu. Uncensored IA. Qu'est-ce que l'API sans tête. Dolphin IA. Modelos IA privados. IA sem censura. API recherche web IA. Migliori chatbot IA senza filtro. IA sem filtro. IA sans censure. Abliterated IA. Gemini sans censure. Uncensored model. Cheap LLM API. Uncensored AI. OpenAI API alternative. Uncensored AI chat. Uncensored chatbot. Ia texte sans censure.