API Quickstart

Base URL and Authentication

Start by pointing your client to our base URL and passing your key in the header. We use the standard Authorization scheme, so any OpenAI SDK or compatible client works immediately. You do not need to manage complex OAuth flows or wait for approval. Just sign up with Google or email, copy the key, and you are ready. The endpoint is https://api.aiohnezensur.com/v1 and accepts the Authorization: Bearer YOUR_API_KEY header on every request.

Sending Your First Request

Make a simple chat completion call to test the uncensored model. This request sends a prompt and receives a text response without the usual corporate guardrails. You can use any tool that supports the OpenAI protocol, but a direct curl call shows exactly what happens under the hood. Replace YOUR_API_KEY with your actual key from the dashboard.

Copycurl https://api.aiohnezensur.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list 5 free open source image generators"}]
  }'

The response includes the generated text and token usage statistics. If you get a response, your integration is working correctly. You can now proceed to build more complex interactions or switch to programmatic clients.

Python SDK Integration

Use the official OpenAI Python package to interact with our API seamlessly. Set the base URL to our endpoint and provide your key as the API token. This allows you to leverage existing codebases without rewriting the HTTP logic. The model ID is uncensored, which triggers our specific large language model tuned for unrestricted output.

Copyfrom openai import OpenAI

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

This snippet demonstrates a basic message exchange. You can adjust the messages array to include system prompts or conversation history. The SDK handles the serialization and error parsing for you.

Node SDK Integration

Integrate the API into your JavaScript or TypeScript applications using the Node SDK. Configure the base URL and API key just like the Python example. This approach works well for server-side rendering or backend microservices. The SDK abstracts the network layer, letting you focus on the prompt logic.

Copyimport OpenAI from "openai";

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

Run this code to see the model respond to your input. You can iterate quickly by changing the prompt content. The response structure matches the standard OpenAI format, ensuring compatibility with other tools in your stack.

Streaming Responses

Enable streaming to receive tokens as they are generated, reducing perceived latency. This is crucial for user interfaces that display text in real-time. Set the stream parameter to true in your request. The API sends a series of Server-Sent Events (SSE) instead of a single JSON object. Each chunk contains a partial delta of the response.

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)

Concatenate these deltas on the client side to reconstruct the full message. This method feels instant to the user, even for long outputs. The final chunk contains the total token usage, allowing you to bill accurately.

Rate Limits and Constraints

Understand the technical limits to prevent request failures in production. You are allowed 300 requests per minute per key and can have 8 concurrent requests. The request body must not exceed 8 MB. If you exceed these limits, the API returns a 429 status code. You should implement exponential backoff in your client to handle these spikes gracefully. Context window is 100,000 tokens total, with a max output of 16,000 tokens per request. Errors and refusals do not consume credit, so you can retry safely. Authentication errors return 401, and insufficient funds return 402.