Documentación de la API Uncensored

Autenticación y Base URL

The API is an OpenAI-compatible endpoint. Use the base URL https://api.iasinrestricciones.com/v1 and pass your API key in the Authorization header. Authentication is simple: create an account via Google or email, and your key is shown immediately. No phone number is required. The key grants access to the uncensored model without monthly subscriptions.

You can generate a new key at any time, which replaces the old one. Keep your key secure, as it controls your prepaid credits. Errors and refusals do not consume your balance, ensuring transparent pricing.

Endpoint: POST /v1/chat/completions

Send messages to the uncensored model to receive text responses. This endpoint handles all conversational logic. You can stream results or receive the full completion at once. The model supports tools, JSON mode, and various sampling parameters.

• Input: JSON payload with messages array.
• Output: Standard chat completion response.
• Max output: 16,000 tokens per request.

Copycurl https://api.iasinrestricciones.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 Peru"}]
  }'

Endpoint: GET /v1/models

Verify available models and their configurations. This endpoint returns a list of models accessible to your API key. It is useful for checking the model ID or retrieving metadata. The response includes the model identifier and pricing information.

• Method: GET
• Path: /v1/models
• Response: JSON object with model details.

Copyfrom openai import OpenAI

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

Parámetros: Temperature, Top-p, Stream

Control the creativity and format of responses. Adjust temperature for randomness, top_p for nucleus sampling, and stream for real-time token delivery. These parameters allow fine-tuning of the uncensored model's output style.

• Temperature: Controls randomness (0.0 to 2.0).
• Top-p: Nucleus sampling threshold.
• Stream: Enable SSE for incremental output.

Copyimport OpenAI from "openai";

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

Modelo 'uncensored' y limitaciones

The uncensored model is an open-weight LLM tuned for unrestricted responses. It does not refuse lawful adult, fictional, or controversial topics. However, it strictly enforces a hard limit: no sexual content involving minors. This model is not GPT, Claude, or any other vendor's model. It runs on our dedicated servers.

Context window: 100,000 tokens (prompt + completion). Max output: 16,000 tokens. Requests exceeding these limits return an error. Prompts are not used for training.

Formato de respuesta y uso de tokens

Responses follow the standard OpenAI format. Token usage is reported in the final chunk when streaming. Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. Prepaid credit never expires.

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)