Direct Uncensored API

Uncensored Chat API for Developers

A hosted, OpenAI-compatible chat API running one dedicated uncensored model. Get text responses without model aggregation or content refusals for lawful adult use.

One dedicated uncensored model
$0.25/$1.00 per 1M tokens
Crypto billing only, no card

Get API key Read the docs

Try it in one request

curl https://api.uncensoredchat.top/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."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredchat.top/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.uncensoredchat.top/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);

$0.25
per 1M input tokens: $1.00
Output tokens / 1M: 64,000
token context: $0.50
trial credit: 300
requests per minute

What you get

OpenAI Compatible

Works with official OpenAI SDKs by changing base_url to https://api.uncensoredchat.top/v1. No custom clients needed.

Transparent Pricing

Pay only for real token usage. Errors and refusals are free. Credit never expires and has no monthly fees.

Crypto Top-ups

Top up via USDT (TRC20) or USDC (Base). Amounts from $10 to $500 with bonus credit for larger deposits.

Streaming & Tools

Supports SSE streaming, function calling, and JSON mode. Full control via standard parameters like temperature and top_p.

Large Context Window

Supports 64,000 tokens context. Max output is 16,000 tokens per request, or 2,048 if max_tokens is unset.

Instant Access

How it works

Sign Up

Create an account via Google or email to get your API key instantly.

Top Up

Add crypto credit (USDT or USDC) to your account to start making requests.

Integrate

Point your OpenAI-compatible client to our base URL and start sending prompts.

What people build with it

Unrestricted Generation

Generate text without filters for adult themes, controversial topics, or creative fiction. The model answers directly without unnecessary refusals.

Security Research

Test LLM vulnerabilities and jailbreaks without hitting standard content gates. Ideal for red-teaming and prompt engineering analysis.

Content Creation

Write NSFW stories or roleplay scenarios without paying for features you don't need. Get clean text output every time.

Developer Testing

Use the free trial to verify streaming, tool use, and JSON modes in your application before committing to prepaid credit.

Why Direct Inference Beats Aggregation

Aggregators mix models and add routing layers that can introduce latency or unexpected behavior. We run one dedicated uncensored large language model on our own servers. This guarantees a consistent response style and predictable performance. You get a single inference engine tailored for unrestricted use, not a lottery of different models.

Our API is simple: text in, text out. We don't aggregate other vendors' models. This means no surprise routing changes and no hidden costs from multiple upstream providers. You know exactly which model is processing your request.

API Specs: OpenAI Compatible & Fast

Our API follows the OpenAI chat-completions standard. Use the official SDKs by updating the base_url to https://api.uncensoredchat.top/v1. The model id is "uncensored". We support streaming via Server-Sent Events, function calling, and JSON mode.

Key limits include a 64,000 token context window and 8 requests per second per key. Request bodies are limited to 8 MB. We do not offer embeddings, image generation, or fine-tuning. Keep your integration simple and focused on text generation.

Transparent Token Pricing & Crypto Billing

Price: $0.25 per 1M input tokens, $1.00 per 1M output tokens. You pay only for actual usage. Errors and refusals do not charge you. Credit never expires and there are no monthly subscriptions.

Top-ups are crypto only: USDT (TRC20) or USDC (Base). Minimum $10, maximum $500 per transaction. Bonus credit applies at $50 (+5%) and $100 (+10%). No credit cards, PayPal, or bank transfers. Refunds are not issued, but double charges are fixed via Support.

Built for Adult & Unrestricted Content

The model is tuned to answer without content refusals for lawful adult use. It handles controversial topics, fiction, and security research without filtering. The only hard limit is sexual content involving minors, which is always refused.

Prompts are not used for training. Your data remains private. This is a direct uncensored chat API for developers who need reliable, unrestricted text generation without the noise of general-purpose models.

Start with $0.50 Free Trial

Every new account gets $0.50 of trial credit valid for 7 days. No card needed. Sign up with Google or email to get your key immediately. One trial per person.

This is not for you if you need image generation, audio, video, or embeddings. We are a text-only API. If you need model routing or SLA guarantees, look elsewhere. We offer a straightforward, uncensored text API with transparent crypto billing.

Questions and answers

What is the base URL for the API?

The base URL is https://api.uncensoredchat.top/v1. You can use this with any OpenAI-compatible client by updating the base_url configuration.

How do I top up my account?

Top ups are accepted via USDT (TRC20) or USDC (Base) only. Minimum amount is $10, maximum is $500. No credit cards or PayPal are accepted.

Does the model refuse adult content?

No, the model is tuned for unrestricted use and does not refuse lawful adult content. The only hard limit is sexual content involving minors, which is always refused.

What is the context window size?

The context window is 64,000 tokens for prompt and completion combined. The maximum output per request is 16,000 tokens.

Is the trial credit recurring?

No, each account gets one $0.50 trial valid for 7 days. No card is needed to start. Top up with crypto to continue using the API.

Your key is one form away

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

Get API key Read the docs