Uncensored AI Generator API Quickstart

Authentication & Base URL

To start using the uncensored llm api, you need a valid API key. Sign up via Google or email on the Get API key page to receive your key immediately. No phone number is required, and no card is needed for the initial trial.

Set your base URL to https://api.uncensoredaigenerator.top/v1. Pass your key in the Authorization header as a Bearer token. This setup works with any standard OpenAI-compatible client, allowing you to swap your base URL and key without changing your integration logic.

Keep your key secure. Each account supports one active key; generating a new one replaces the old. Requests are authenticated on every call, ensuring your uncensored text generation remains private and secure.

Chat Completions Endpoint

The core of the uncensored AI generator is the POST /v1/chat/completions endpoint. Send your prompt in the messages array and specify the model as uncensored. The API returns text completions optimized for adult content pipelines, handling dialogue, script writing, or post-processing without content refusals.

Use the system role to define the persona or context for your NSFW AI generator. This helps maintain consistency across long conversations. The API accepts standard parameters like temperature and top_p to control creativity.

Ensure your requests stay within the 64,000 token context window. The model processes both prompt and completion tokens together, so plan your input size accordingly.

Streaming Responses

For real-time text generation, use Server-Sent Events (SSE). Streaming is ideal for chat interfaces where you want to display tokens as they are generated. The uncensored AI generator API supports streaming by setting stream: true in your request.

Each chunk contains partial text, and the final chunk includes token usage statistics for billing. This allows you to update your UI incrementally while keeping track of costs accurately. Streaming reduces perceived latency for users engaging with your NSFW AI generator.

Handle stream completion events to know when the response is finished. This ensures your application can process the full response and prepare for the next interaction without waiting for the entire block to load.

Parameters for NSFW Content

Control the output style using parameters like temperature and top_p. Lower temperatures produce more deterministic responses, while higher values increase creativity. Use stop sequences to truncate output at specific points, useful for formatting dialogue or scripts.

Enable JSON mode with response_format: {"type": "json_object"} for structured data extraction or prompt engineering workflows. The uncensored llm api respects these parameters while maintaining its uncensored nature for lawful adult content.

Use seed for reproducible results during testing. Function calling is supported via tools and tool_choice for integrating external tools into your NSFW AI generator pipeline.

Rate Limits & Errors

Each API key is limited to 300 requests per minute and 8 concurrent requests. If you exceed these limits, you will receive a 429 error. The request body size is capped at 8 MB.

Common errors include 401 for invalid keys and 402 for insufficient credit. Errors and refusals are free, so you are not charged for failed requests. Credit is charged only for successful token usage.

The uncensored AI generator API refuses sexual content involving minors in all cases. Other adult content is generally permitted. Check the error response for details on rate limits or billing issues.

Model Info

The model ID is uncensored. It is an open-weight model run on our own servers, distinct from GPT, Claude, or other vendors. It is tuned for adult content pipelines and does not refuse lawful NSFW topics.

The context window is 64,000 tokens, including both prompt and completion. The maximum output per request is 16,000 tokens, or 2,048 if max_tokens is not set.

Billing is transparent: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Credit never expires. Use the GET /v1/models endpoint to verify available models and their details.

cURL

Copycurl https://api.uncensoredaigenerator.top/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python

Copyfrom openai import OpenAI

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