Developer-First API

Uncensored AI: The OpenAI-Compatible LLM API for Developers

A pure, OpenAI-compatible chat-completions API serving a dedicated uncensored large language model. Integrate immediately with zero learning curve for your existing AI workflows.

OpenAI-compatible endpoint
64k context window
Crypto prepaid credit

Get API key Read the docs

Try it in one requestuncensored

curl https://api.uncensoredai.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.uncensoredai.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.uncensoredai.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);

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

What you get

Pure API Focus

We provide only the chat-completions endpoint for text generation. No embeddings, images, audio, or video generation to clutter your integration.

Streaming & JSON

Supports SSE streaming with token usage in the last chunk. Enforce strict JSON output with response_format or use function calling with tools.

Large Context Window

Process up to 64,000 tokens per request (prompt + completion). Generate up to 16,000 tokens in a single response for long-form tasks.

True Uncensored Model

Our open-weight model answers without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.

Simple Crypto Payments

Top up with USDT (TRC20) or USDC (Base) from $10 to $500. Credit never expires and errors/refusals are charged zero tokens.

Instant Access

Sign up with Google or email to get your API key immediately. No phone number required, and every new account receives $0.50 trial credit.

How it works

Get Your Key
Sign up via Google or email on the dashboard to generate your unique API key instantly.
Set Base URL
Configure your client to point to https://api.uncensoredai.top/v1 and inject your API key.
Send Requests
Send POST requests to /v1/chat/completions with model id "uncensored" and start generating text.

What people build with it

Content Generation

Generate creative writing, stories, or marketing copy without standard corporate filters blocking nuanced or adult themes. Ideal for media that requires fewer restrictions.

Security Research

Prompt LLMs to break out of jailbreak patterns or analyze model weaknesses without them refusing due to standard safety refusals. Get raw model outputs.

Data Processing

Use JSON mode to reliably extract structured data from unstructured text. The dedicated model ensures consistent formatting without unexpected refusal interruptions.

Roleplay & Chat

Build chatbots that maintain character and context over long sessions. The 64k context window allows for deep, continuous conversations without losing track.

The Uncensored AI API Endpoint

The Uncensored AI API provides a single, dedicated endpoint for text generation. Unlike aggregators that route through multiple models, we serve one open-weight model tuned for minimal refusals. This ensures consistent behavior and predictable latency for your applications. You interact with a standard chat-completions interface that accepts text and returns text.

Our architecture is simple: POST /v1/chat/completions and GET /v1/models. There are no embeddings, no image generation, and no fine-tuning endpoints to manage. This reduction in complexity means fewer points of failure and a faster integration process. You get exactly what you ask for, without the overhead of a multi-model platform.

OpenAI SDK Compatibility

Because we follow the OpenAI API specification, you can use the official SDKs or any compatible client with minimal configuration. Simply update the base_url to https://api.uncensoredai.top/v1 and provide your API key. The model identifier is "uncensored". This means existing code for GPT-4 or GPT-3.5 often works with zero code changes, only requiring a URL update.

This compatibility extends to standard parameters like temperature, top_p, stop sequences, and seed. You can leverage existing tooling and wrappers built for OpenAI without rewriting your logic. Check the official OpenAI documentation for the full list of supported parameters, as our implementation mirrors their standard behavior.

Developer Features: Streaming, JSON, Tools

We support streaming via Server-Sent Events (SSE), allowing you to receive tokens as they are generated. The final chunk includes the total token usage for accurate billing and monitoring. For structured data needs, use response_format set to json_object to enforce strict JSON output, which is critical for programmatic pipelines.

Function calling is fully supported, allowing you to define tools and let the model decide when to invoke them. You can control tool choice behavior and pass multiple arguments. This makes the uncensored llm api suitable for complex agent workflows where reliable tool execution is required without standard refusal filters interfering with valid tool use.

Who This Is (And Isn't) For

This API is for developers who want a straightforward, pay-as-you-go solution for uncensored text generation. If you need a chat interface, image generation, or embeddings, this is not the right product. We do not offer SLA percentages, SOC2/HIPAA/ISO certifications, or on-prem deployment. If you require enterprise-grade compliance or model routing between multiple vendors, look elsewhere. We are a focused tool for a specific need: raw, uncensored text output via a simple API.

Questions and answers

What is the context window limit?

The context window is 64,000 tokens, counting both the prompt and the completion together. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the default output limit is 2,048 tokens.

How do I pay for the API?

We accept crypto only: USDT (TRC20) or USDC (Base). You can top up any whole amount between $10 and $500. Credit never expires, and you receive a +5% bonus for $50+ and +10% for $100+ tops.

Is there a free trial?

Yes, every new account gets $0.50 of trial credit valid for 7 days. No credit card is needed to sign up. You can start generating immediately after verifying your email or Google account.

Does the model refuse content?

The model is tuned to answer without refusals for lawful adult use, including controversial or fictional topics. However, we have a hard limit: sexual content involving minors is always refused. Requests containing that content will be blocked.

What are the rate limits?

You are limited to 300 requests per minute per key and 8 concurrent requests per key. The maximum request body size is 8 MB. Each account is limited to one active key; generating a new key replaces the previous one.

Your key is one form away

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

Get API key