API Documentation

Base URL and Authentication

Connect your client to our single API endpoint using the standard OpenAI SDK configuration. Use HTTPS://api.restrictionswithoutai.com/v1 as your base URL and assign your unique key to the API_KEY environment variable. This setup works with any library that supports the OpenAI chat-completions protocol. You can sign up using Google or an email password. Your key grants access to one uncensored model. The endpoint is strictly for text generation. We do not offer embeddings, images, or audio processing. Keep your key secure. It identifies your prepaid account. Errors and refusals do not consume your tokens. This ensures you only pay for actual output. Our infrastructure handles the heavy lifting. You get direct access to the model.

First Request

Make your initial call to generate text using the POST /v1/chat/completions endpoint. Specify the model ID as uncensored to ensure you get the unfiltered responses you need. The request body must include a messages array containing your system and user prompts. This approach mirrors standard OpenAI integrations. You can adjust parameters like temperature to control randomness. The model responds with generated text in the choices array. Check the usage field to see token consumption. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. These rates apply to prepaid credit only. No hidden fees exist. No monthly subscriptions apply. You control your spending. Top up via crypto whenever needed. The system tracks usage accurately. Errors are free. Refusals are free. This transparency keeps costs low. Start with a simple query. Observe the response structure. Adjust your client code accordingly.

Python SDK Integration

Use the official OpenAI Python library to interact with our API seamlessly. Set the base URL to our endpoint and provide your API key. This allows you to leverage familiar methods like chat.completions.create. You can define system instructions to guide the model. User messages drive the conversation. The library handles serialization and authentication. Streaming is supported for real-time token display. Function calling works out of the box. JSON mode ensures structured outputs. Error handling follows standard SDK patterns. Rate limits return 429 status codes. Authentication failures return 401. Insufficient funds return 402. These codes help you debug quickly. The SDK abstracts the HTTP details. Focus on your application logic. The model context window is 100,000 tokens. This allows for long conversations. Keep prompts concise. Optimize your token usage. Track costs in your dashboard. Crypto payments simplify billing. No bank accounts needed. Just top up and code.

Node.js SDK Integration

Integrate with Node.js applications using the standard OpenAI SDK for JavaScript. Configure the base URL to point to our API. Pass your API key in the configuration object. This enables direct communication with the uncensored model. You can create completions with async/await syntax. The response structure matches OpenAI standards. Handle errors gracefully. Check for rate limits. The SDK supports streaming responses. This is useful for chat interfaces. Display tokens as they arrive. The model supports tool definitions. You can pass functions for execution. JSON mode forces structured output. This helps with data parsing. Use environment variables for keys. Avoid hardcoding secrets. The context window is large. Manage memory usage efficiently. Process chunks as they come. The API is reliable. Payments are instant. Crypto only. Top up with USDT or USDC. Start building your app today.

Streaming Responses

Enable streaming to receive tokens in real-time via Server-Sent Events (SSE). Set the stream parameter to true in your request. The API returns a series of chunks. Each chunk contains partial text. This reduces perceived latency for users. The final chunk includes usage statistics. Token counts appear in the last response. This allows accurate billing tracking. Streaming works with all SDKs. Python and Node libraries handle this automatically. You can parse raw SSE if needed. The model generates text continuously. This improves user experience. Chat applications benefit significantly. Display tokens as they arrive. Cancel the stream if needed. The API supports concurrent streams. Limits apply per key. Eight simultaneous requests allowed. Rate limit is 300 requests per minute. Monitor your usage. Top up when credits run low. Crypto payments are instant. No waiting for bank clears. Just pay and play. Stream your content.

Limits, Errors, and Context

Understand the operational limits to optimize your integration. The context window is 100,000 tokens total. This includes prompt and completion. Max output is 16,000 tokens per request. Default max is 2,048 tokens. Set max_tokens explicitly for control. Rate limit is 300 requests per minute. You can have 8 concurrent requests. Request body size is limited to 8 MB. Errors return specific HTTP codes. 401 indicates an invalid key. 402 means no credit. 429 signals rate limiting. Handle these codes in your app. Refunds are not issued for credit. Mistakes are fixed via support. Credit never expires. One active key per account. Replace the old key to generate a new one. Privacy is strict. Prompts are not used for training. No data mining. Just use the API. Focus on your product. We handle the infrastructure. Reliable and uncensored.

cURL

Copycurl https://api.restrictionswithoutai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check if port 8080 is open"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.restrictionswithoutai.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.js

Copyimport OpenAI from "openai";

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

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)