Quickstart Guide

Prerequisites: Get your API key

Start by securing your access credential on the dashboard. You can sign in with Google or use an email and password. No phone number is required for this minimal account setup. Once registered, your unique API key is displayed immediately. You only need one active key per account, as generating a new one replaces the old. This direct approach ensures you can begin integrating without administrative friction or unnecessary verification steps that often delay developer workflows.

Base URL and authentication

Configure your client to point to our specific endpoint. Use https://api.aisenzalimitietici.com/v1 as your base URL. Pass your key in the Authorization header with the Bearer prefix. This standard format ensures compatibility with existing tools. You do not need to modify complex routing logic. Just update the base URL in your SDK configuration and inject your key. This simple setup allows you to leverage the same client libraries you already trust for other models.

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

Sending your first request

Execute a standard chat completion to verify connectivity. Send a POST request to /v1/chat/completions with the model ID uncensored. Include your system prompt to define the behavior. The model will return a response without the typical corporate refusals. You can send text in and receive text out immediately. This direct interaction confirms that your key is valid and the connection is stable. Check the content field in the response to see the generated text.

Copyfrom openai import OpenAI

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

Streaming responses (SSE)

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events stream instead of a single JSON object. Each chunk contains partial text until the final token is sent. This approach reduces perceived latency significantly. You can display tokens to the user as they are generated. The last chunk also includes the final usage statistics. This feature is essential for building responsive chat interfaces that feel immediate and fluid.

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)

Advanced parameters (Temperature, Top-p)

Control the creativity and determinism of the output. Adjust temperature to vary randomness. Lower values produce more consistent results. Higher values encourage diverse and creative responses. Use top_p to control the nucleus sampling. Set response_format to json_object if you need structured data. You can also use stop sequences to halt generation. These parameters give you precise control over how the model constructs its answers.

Error handling and limits

Monitor your requests for standard HTTP status codes. A 401 error indicates an invalid key. A 402 error means you need to top up your crypto credit. A 429 error signals that you have hit the rate limit of 300 requests per minute. The context window supports 100,000 tokens total. If you exceed the output limit of 16,000 tokens, the generation stops. Always check the response body for detailed error messages. This transparency helps you debug issues quickly without guessing.

Node.js

Copyimport OpenAI from "openai";

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