Uncensored LLM API

Uncensored api for Developers

Deploy a reliable uncensored API with a 100,000-token context window, prepaid crypto billing, and zero monthly subscription lock-in.

Start now View documentation

Postpaid crypto top-ups only
100,000-token context window
$0.50 per 1M output tokens

Test with one request

curl https://api.apiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Get the current server status code for the production environment"}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

Core features

OpenAI-Compatible

Works with standard OpenAI SDKs by changing the base URL and API key.

No Refusals

Our uncensored LLM model answers lawful adult and controversial topics without generic refusals.

Prepaid Credit

Pay only for real token usage; errors and refusals are free with no monthly fee.

Crypto Only

Top up with USDT (TRC20) or USDC (Base) from $20 to $500 for bonuses.

Streaming Support

Access token usage in the last chunk via Server-Sent Events for real-time responses.

JSON Mode

Enforce structured outputs with response_format json_object for reliable programmatic integration.

Setup process

Create Account

Add Crypto Credit

Top up via USDT or USDC to receive bonus credits and start billing.

Integrate SDK

Update your base URL to ours and send requests to the chat-completions endpoint.

Community projects

NSFW Content Generation

Reliably process adult themes without random refusals or context-dependent gating errors.

Security Research

Analyze jailbreaks and model behaviors with an unfiltered LLM that accepts heavy themes.

Unfiltered Chatbots

Build conversational agents that answer any lawful request without corporate safety filters.

Long-Context Analysis

Process large documents using a 100,000-token context window for comprehensive analysis.

The uncensored API that actually delivers

We provide a hosted, OpenAI-compatible API serving a single uncensored LLM tuned to answer without refusals for lawful adult use.

Direct Integration

Send requests to POST /v1/chat/completions using standard SDKs. The model id is uncensored and the base URL is HTTPS://api.apiuncensored.com/v1.

Predictable Billing

Pay only for real token usage with prepaid crypto. Errors and refusals cost nothing, and your credit never expires.

No Lock-in

Get a key instantly via Google or email.

Who uses the uncensored API and who should skip it

Developers building NSFW LLM applications or security research tools need this service. Our uncensored AI handles controversial topics without refusals.

Use it for chatbots requiring raw output.
Skip it if you need image generation or embeddings.

It lacks fine-tuning and streaming is optional. You get one key per account. The model id is "uncensored". Context windows support 100,000 tokens. Errors are free.

Get your key in 3 steps

Access the API immediately after signing up. Use your credentials to start sending requests.

Sign up. Click Continue with Google or enter an email and password. No phone number is required. Your API key appears instantly.
Add credit. Top up with USDT (TRC20) or USDC (Base). Minimum $20. Get 5% bonus credit at $50.
Call the API. Point your OpenAI SDK to https://api.apiuncensored.com/v1. Send a POST request with model uncensored.

Signs you have the right uncensored API provider

Reliable content delivery requires strict adherence to specific operational signals. The table below outlines six concrete indicators that distinguish a robust uncensored LLM service from generic wrappers.

Token cost breakdown and examples

Our uncensored API charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals cost nothing. A 5000-input/2000-output request costs roughly $0.00175. This prepaid model eliminates subscription lock-in, letting you scale usage without monthly fees. Top up via crypto to secure volume bonuses, ensuring your budget stretches further with every top-up tier.

Checklist for choosing an uncensored provider

Verify the billing model matches your volume needs.

Confirm prepaid, pay-per-token billing with no monthly fees.
Ensure errors and refusals are free, not charged.
Check for crypto-only top-ups with volume bonuses.
Validate OpenAI SDK compatibility with simple base_url changes.
Confirm a 100,000-token context window and 300 requests per minute.
Ensure no card is needed for trial access.
Verify privacy: prompts are not used for training.
Confirm one active key per account with easy rotation.

Common questions

What is the uncensored API and how does it work?

It is a hosted chat-completions service. You send text and receive text. The model id is "uncensored". It uses the standard OpenAI-compatible endpoint. You can use existing SDKs by changing the base URL to our server. This works for any client.

Does the uncensored API support streaming responses?

Yes, it supports streaming via Server-Sent Events. You can stream tokens in real time. The final chunk includes the total token usage count. This allows you to display text as it generates. It reduces perceived latency for end-users significantly during long outputs.

Can I use this uncensored API for function calling?

Yes, the API supports function calling. You can define tools in your request. The model can choose to call a tool or return text. You must set the tool_choice parameter. This enables complex workflows without manual parsing of tool names.

What is the context window limit for the uncensored API?

The context window is 100,000 tokens. This includes both the prompt and the completion. You can set a maximum output of 16,000 tokens per request. If you do not set max_tokens, it defaults to 2,048 tokens. This allows for substantial conversation history.

How much does the uncensored API cost per token?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. You pay only for actual usage. Errors and refusals do not charge you. Credit never expires, so you can top up once and use it over time.

What payment methods are accepted for the uncensored API?

We accept crypto only. You can pay with USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. You receive bonus credit for larger amounts.

Get your key instantly

Start now View documentation