Quickstart: Your First Uncensored Request

Prerequisites: Your API Key and Base URL

Start by generating an API key on the Get API key page. You can sign in with Google or use a simple email and password; no phone number is required. The system displays your key immediately, so copy it to your clipboard now.

Our API lives at https://api.alternativeaivenice.com/v1. This base URL works with any official OpenAI SDK by updating the base_url parameter. You only need one active key per account; issuing a new one replaces the previous key instantly.

Making Your First Chat Completion Request

Send a standard chat completion payload to receive raw, uncensored text output. Use the model ID uncensored to access our open-weight model tuned for lawful adult use without content refusals.

Below is a basic cURL request demonstrating the structure. Replace YOUR_API_KEY with your actual key to see the model respond to your prompt.

Copycurl https://api.alternativeaivenice.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top ten programming languages"}]
  }'

Streaming Responses with Server-Sent Events

For real-time interaction, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE) where token usage details appear in the final chunk.

This approach reduces perceived latency for long responses. Use the Python snippet below to handle the stream efficiently in your application.

Copyfrom openai import OpenAI

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

Using JSON Mode for Structured Data

Force structured output by setting response_format to {"type": "json_object"}. This ensures the model returns valid JSON, which is ideal for parsing data into your backend systems.

You can also use function calling with the tools parameter. The Node.js example below shows how to configure this for reliable parsing.

Copyimport OpenAI from "openai";

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

Understanding Context Windows and Limits

Our model supports a context window of 100,000 tokens, covering both prompt and completion. You can generate up to 16,000 tokens per request, or 2,048 if you omit max_tokens.

Rate limits allow 300 requests per minute and 8 concurrent requests per key. The request body must stay under 8 MB. These limits ensure stable performance for your uncensored LLM integrations.

Troubleshooting Common Errors

401 Unauthorized means your API key is invalid or expired. Regenerate a key from your dashboard. 402 Payment Required indicates insufficient prepaid credit. Top up via crypto to continue. 429 Too Many Requests signals you have hit the 300 requests per minute limit.

Refusals are rare but apply to sexual content involving minors. Errors during processing do not consume your credit, so you can retry safely.

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)