Get API key

Uncensored LLM API for developers

Looking for Minicpm? Read this first

An OpenAI-compatible API running a single uncensored model. Drop it into your existing code to bypass content filters without changing your SDK.

  • $0.25 per 1M input tokens
  • 100k context window
  • Crypto payments only

Uncensored LLM API for developers

per 1M input tokens
$0.25
Output tokens / 1M
$1.00
token context
100,000
trial credit
$0.50
requests per minute
300

No subscription. Prepaid credit never expires.

Try it in one request

curl https://api.minicpm.cc/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."}]
  }'

What you get

Drop-in Replacement

Uses the standard /v1/chat/completions endpoint. Swap your base URL and API key to start sending requests with any OpenAI SDK.

One Uncensored Model

The model ID is 'uncensored'. It answers controversial, adult, and security topics without the refusals common in generic models.

Transparent Pricing

Pay only for tokens used. Errors and refusals are free. No monthly subscriptions or hidden fees.

Crypto Top-ups

Fund your account with USDT (TRC20) or USDC (Base). Bonuses apply to larger deposits.

Streaming Support

Receive responses via Server-Sent Events (SSE). Token usage details are included in the final chunk.

Developer First

No phone number required. Sign up with Google or email. Get your key instantly.

How it works

  1. Get Your Key

    Sign up with Google or email and receive your API key immediately.

  2. Update Base URL

    Change your client configuration to point to https://api.minicpm.cc/v1.

  3. Send Requests

    Use the model ID 'uncensored' in your standard chat completion calls.

What people build with it

Content Filtering Removal

Use the API for creative writing or roleplay where standard models refuse adult or controversial themes. It answers directly without extra politeness filters.

Security Research

Query the model for technical security topics or controversial opinions without worrying about ideological bias blocking the response.

LLM Fine-tuning Data

Generate large volumes of text for training data. Pay only for the tokens you actually use without a monthly commitment.

Dev Testing

Test your application's handling of uncensored responses. Use the trial credit to verify behavior before committing to a crypto deposit.

Quick Start: One API Key

To start using the minicpm API, you need an API key. Sign up using Google or your email address. No phone number is required. Your key is displayed immediately upon registration.

  • Base URL: https://api.minicpm.cc/v1
  • Model ID: uncensored
curl https://api.minicpm.cc/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."}]
  }'

The API supports standard parameters like temperature, top_p, stop, and seed. You can also enable JSON mode using response_format.

Model: Uncensored LLM

The API serves a single open-weight model optimized for minimal refusals. It is tuned to answer lawful adult, fictional, and controversial topics directly. The model ID is uncensored.

Context Window: 100,000 tokens total (prompt + completion).
Max Output: 32,000 tokens per request (2,048 if max_tokens is unset).

Content Limits: The model does not refuse general adult content. However, a hard limit applies: requests involving sexual content with minors are always refused. This is the only strict filter.

This is NOT GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or Mistral. It is an independent model run on our servers.

Pricing: Pay Per Token

We charge based on real token usage. Errors and refusals do not consume credits.

  • Input: $0.25 per 1M tokens
  • Output: $1.00 per 1M tokens

from openai import OpenAI

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

Credit never expires. There are no monthly fees. Mistakes like double charges are handled via the Support page.

Crypto Payments

Top up your account using cryptocurrency. We accept USDT (TRC20) and USDC (Base). Any whole amount from $10 to $500 is accepted.

Bonuses: Deposits of $50 or more receive a 5% bonus credit. Deposits of $100 or more receive a 10% bonus credit.

import OpenAI from "openai";

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

No credit cards, PayPal, or bank transfers. The trial gives you $0.50 valid for 7 days.

Questions and answers

What is the model ID?

The model ID is 'uncensored'. Use this value in your API requests to select the model.

Does it support streaming?

Yes. The API returns Server-Sent Events (SSE). Token usage details are included in the last chunk of the stream.

How do I pay?

You can only pay with crypto: USDT (TRC20) or USDC (Base). Minimum deposit is $10. No credit cards are accepted.

What content is blocked?

The model is uncensored but has one hard limit: sexual content involving minors is always refused. All other lawful adult content is allowed.

Who is this NOT for?

This is NOT for users needing image generation, embeddings, or audio. It is also not for users who prefer a subscription model or need multiple model options. If you need SLA guarantees or SOC2, this independent API is not the right fit.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key