Documentación de la API OpenAI Compatible

Base URL y Autenticación

Start by pointing your SDK to our base URL: https://api.generadordepromptssincensura.com/v1. Authentication uses a single API key passed as a Bearer token in the Authorization header. Get your key instantly via Google or email on the Get API key page; no phone number is required. Each account holds one active key, which is displayed immediately upon creation. This setup works with any OpenAI-compatible client, allowing you to swap base URLs without changing your code structure. Your prompts are not used for training, ensuring privacy while you generate content.

Endpoint: POST /v1/chat/completions

Send text in and get text out using the standard chat completions endpoint. The model ID is uncensored, an open-weight model tuned for lawful adult and unrestricted content without refusals. You can send parameters like temperature, top_p, and stop to control generation. Errors and refusals are free, so you only pay for real token usage. The context window supports 100,000 tokens total, with a max output of 16,000 tokens per request. Use this endpoint for roleplay, NSFW stories, or deep analysis where standard models might filter your input.

Streaming con SSE y Uso de Tokens

Stream responses efficiently using Server-Sent Events (SSE). Token usage details are included in the final chunk of the stream, allowing you to track costs in real-time. This method reduces perceived latency for long outputs, which is critical for uncensored chatbots and interactive roleplay sessions. You can set max_tokens to cap output length; if unset, the default is 2,048 tokens. Streaming ensures your application remains responsive even when generating extensive narratives or code blocks without blocking the main thread.

Modelo 'uncensored' y Contexto de 100k

Our model is not GPT, Claude, or any other vendor's product; it is a distinct uncensored AI model running on our servers. It answers without content refusals for controversial or adult topics, provided they are lawful. The 100,000-token context window allows you to paste entire books or codebases for deep analysis. Requests involving sexual content with minors are always refused. This model excels at creative writing and unrestricted dialogue, offering a raw alternative to moderated LLMs without the need for complex prompt engineering to bypass filters.

Funciones: Tool Calling y JSON Mode

Enable structured outputs with JSON mode by setting response_format to json_object. This ensures predictable parsing for your applications, whether you are building agents or extracting data. Tool calling (function calling) is fully supported, allowing the model to execute actions based on your defined tools. You can control tool behavior with tool_choice and tools parameters. This functionality works alongside temperature and seed settings, giving you precise control over deterministic outputs when needed for production-grade integrations.

Ejemplo de Código Python/Node.js

Integrate quickly using official SDKs. Pass your API key and base URL to initialize the client. Make a simple request to test connectivity before scaling up. The code samples below demonstrate basic text generation and streaming. Remember that prepaid credit is charged by real token usage, and errors are free. You can top up with crypto at any time. The SDK handles retries and rate limits automatically, so you can focus on building your application logic without worrying about the underlying infrastructure.

cURL

Copycurl https://api.generadordepromptssincensura.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of five key features for this API"}]
  }'

Python

Copyfrom openai import OpenAI

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