How do I top up my credit?

You can top up using crypto only. We accept USDT (TRC20) or USDC (Base) for amounts between $20 and $500. You receive bonus credit for larger deposits, starting at +5% for $50 and up to +15% for $200.

What happens if I run out of credits?

Your API key remains active, but requests will return a 402 status code indicating insufficient funds. You can add more crypto credit at any time to resume service without losing your key or settings.

Is the uncensored model suitable for adult content?

Yes, the model is tuned to avoid refusals for lawful adult, fictional, or controversial topics. The only hard limit is sexual content involving minors, which is always refused. All other content is generated based on your prompt.

Uncen.com ドキュメント - OpenAI互換APIリファレンス

Authentication and Base URL

Start by configuring your client to point at our infrastructure. Use https://api.uncencom.com/v1 as your base URL and pass your API key in the Authorization header. This setup works with any standard OpenAI-compatible SDK.

curl https://api.uncencom.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"}]
  }'

Authentication failures return a 401 status if the key is invalid. Ensure you copy the key immediately after signup, as it is shown only once.

Chat Completions Endpoint

Interact with the model by sending POST requests to /v1/chat/completions. The model ID is uncensored, and it responds with text based on your system and user prompts. This endpoint handles all standard chat interactions without extra complexity.

from openai import OpenAI

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

The API returns structured JSON containing the generated text. You can adjust behavior using parameters like temperature and top_p to control creativity and determinism.

Streaming Responses (SSE)

For lower latency, enable streaming by setting stream: true in your request. The server sends Server-Sent Events (SSE) with incremental token updates. This allows your application to display output progressively.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncencom.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 is efficient for long outputs. The final chunk includes total token usage statistics, helping you track costs in real-time. Use this mode for chat interfaces where immediate feedback matters.

Function Calling and Tools

The API supports structured tool definitions for function calling. Define tools in your request, and the model can return structured arguments for execution. Use tool_choice to enforce specific behaviors or allow the model to decide.

stream = 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)

Tool responses are handled via the standard conversation history. This enables complex workflows where the model generates data for your code to process. Combine this with streaming for responsive dynamic applications.

JSON Mode and Parameters

Ensure deterministic output by using response_format: {"type": "json_object"}. This forces the model to return valid JSON, which is essential for programmatic integration. You can also set seed for reproducible results.

Adjust parameters like presence_penalty and frequency_penalty to refine text style. These controls help reduce repetition and improve coherence in generated content.

Token Limits and Costs

Each request supports a context window of 100,000 tokens, combining prompt and completion. The maximum output per request is 16,000 tokens, or 2,048 if max_tokens is omitted. Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens.

Rate limits allow 300 requests per minute per key. If you exceed limits, you receive a 429 error. Errors and refusals are free, so you only pay for successful token generation.

Uncen.com API Quickstart