OpenAI-Compatible Text API

Uncensored AI Generator API for Developers

A hosted, uncensored LLM API for developers who need reliable text generation without content refusals. Integrate directly using standard OpenAI SDKs with transparent token-based pricing.

OpenAI-compatible chat-completions endpoint
No content refusals for lawful adult use
Crypto-only top-ups, prepaid credit

Get API key Read the docs

Try it in one request

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

from openai import OpenAI

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

import OpenAI from "openai";

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

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

Standard Integration

Works with official OpenAI SDKs by changing the base_url. Uses standard endpoints for chat completions and model listing.

Uncensored Output

The 'uncensored' model answers without refusing lawful adult, fictional, or controversial topics. Only minor content is blocked.

Streaming & JSON

Supports Server-Sent Events for real-time token streaming. Enforce strict JSON output with response_format for reliable parsing.

Large Context Window

Handle up to 64,000 tokens for prompt and completion combined. Max output is 16,000 tokens per request.

Crypto Payments

Top up with USDT (TRC20) or USDC (Base). Prepaid credit never expires, and errors/refusals are free.

Simple Account

How it works

Create Account
Sign up via Google or email to receive your API key instantly.
Configure SDK
Update your OpenAI client to use the uncensored base_url and your new key.
Send Requests
Call the chat completions endpoint with your preferred model parameters.

What people build with it

Content Pipelines

Generate scripts, captions, or post-processing text without filters blocking creative or mature themes. Ideal for automated media workflows.

Data Extraction

Parse unstructured text into JSON structures with high reliability. Use JSON mode to enforce schema compliance for backend systems.

Research & Analysis

Process large documents with a 64k context window. Get uncensored summaries and analysis without model bias on controversial topics.

Game Development

Generate dynamic dialogue or lore without content restrictions. Stream responses for real-time character interactions in applications.

API Overview & Endpoints

The uncensored ai generator provides a straightforward, OpenAI-compatible interface for text generation. We host a single open-weight model tuned for minimal refusal, serving it through standard endpoints. You will primarily interact with POST /v1/chat/completions for generation and GET /v1/models to verify availability. There are no embeddings, image generation, or fine-tuning endpoints to manage. This simplicity allows you to drop our service into existing codebases with minimal refactoring.

The base URL is https://api.uncensoredaigenerator.cc/v1. By updating this URL and providing your API key, your existing OpenAI SDK clients will route requests to our uncensored model. The model id is simply uncensored. This approach ensures that your integration remains portable and predictable, leveraging the same tool_choice and function calling structures you already know.

Model Capabilities: Context & Output

Our model supports a 64,000-token context window, allowing you to pass large documents or extended conversation histories. The maximum output per request is 16,000 tokens, which covers most single-turn generation needs. If you do not specify max_tokens, the model defaults to 2,048 tokens. This capacity makes it suitable for processing lengthy reports, codebases, or long-form creative writing in a single call.

Unlike many filtered models, this uncensored model does not refuse lawful adult content, controversial opinions, or fictional violence. It is designed for developers who want raw output without post-processing for censorship. The only hard limit is the refusal of sexual content involving minors. This consistency allows you to build pipelines that rely on the model answering the prompt as given, rather than guessing which topics might trigger a block.

Developer Features: Streaming & JSON

For low-latency applications, we support Server-Sent Events (SSE) for streaming responses. Token usage details are included in the final chunk, allowing you to track costs in real-time. This feature is essential for user-facing applications where waiting for full completion is unacceptable.

We also support response_format with json_object, ensuring the model outputs valid JSON when required. This is critical for extracting structured data from unstructured text or generating configuration files. Combined with temperature, top_p, and seed parameters, you can fine-tune the randomness and reproducibility of your outputs. Function calling (tools) is fully supported, enabling the model to execute external actions or return structured arguments for your backend logic.

Pricing & Token Costs

We use a transparent, prepaid credit model. Input tokens cost $0.25 per 1M tokens, and output tokens cost $1.00 per 1M tokens. Errors and refusals are free, so you only pay for actual token consumption. There are no monthly subscriptions or hidden fees. Your prepaid credit never expires, making it ideal for projects with irregular usage patterns.

Top-ups are crypto-only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. We offer bonuses: +5% credit for $50+ and +10% for $100+. New accounts receive $0.50 in trial credit valid for 7 days, no card needed. This model eliminates the risk of surprise charges common with subscription services.

Account & Limits

Sign up with Google or an email and password. Your API key is displayed immediately. Each account is limited to one active key; generating a new one replaces the old. This simplifies key management for most developers.

Rate limits are set to 300 requests per minute and 8 concurrent requests per key. The maximum request body size is 8 MB. These limits are generous for most text processing pipelines but ensure fair usage. If you need higher throughput, you can manage multiple keys or scale horizontally. Our API is not for you if you need SLA guarantees, SOC2 certifications, or multi-modal capabilities like image or video generation. We are a text-only tool for developers who need reliability and lack of filters.

Questions and answers

Is this an official OpenAI service?

No, this is an independent service. We provide an OpenAI-compatible API that uses a different, uncensored model. It works with OpenAI SDKs but is not hosted by OpenAI.

What payment methods are accepted?

We accept only crypto: USDT (TRC20) and USDC (Base). No credit cards, PayPal, or bank transfers are supported. Top-ups range from $10 to $500.

Does the model refuse content?

The model is uncensored and does not refuse lawful adult, controversial, or fictional topics. The only hard limit is sexual content involving minors.

Can I use this for function calling?

Yes, we support tools and tool_choice parameters just like the OpenAI API. You can define functions and have the model return structured arguments.

What is the context window size?

The model supports up to 64,000 tokens for the combined prompt and completion. The maximum output length is 16,000 tokens per request.

Your key is one form away

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