Uncensored LLM API

Heretic uncensored API overview

Get reliable text generation from a dedicated uncensored model with a 100,000-token context window, prepaid via crypto, and zero subscription locks for your NSFW workloads.

100,000-token context window
$0.15 per 1M input tokens
OpenAI-compatible endpoints

Get API key View documentation

Test via single request

curl https://api.hereticuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five features of the new release."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.hereticuncensored.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.hereticuncensored.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 capabilities

Dedicated Model

One uncensored model runs on our servers, not a proxy of GPT or Claude.

Crypto Top-ups

Pay with USDT or USDC and receive bonus credit on larger deposits.

No Limits

No monthly fees or tier caps; credit never expires after purchase.

Streaming Support

Use SSE for real-time token delivery with accurate usage counts.

Function Calling

Full tool support with JSON mode and standard parameter tuning.

Simple Auth

Setup process

Create Account

Add Crypto

Top up with USDT or USDC to activate your balance.

Start Coding

Point your OpenAI SDK to our base URL and send requests.

Integration examples

Roleplay Workloads

Run long-form NSFW stories without unexpected refusals or content filters.

Data Extraction

Parse text from diverse sources using a model that does not hedge.

Content Generation

Produce adult fiction or creative writing with full contextual memory.

API Integration

Swap in this endpoint for existing OpenAI-compatible applications easily.

What developers actually ask about this topic

Which models are available?

We serve one uncensored LLM API model, id "uncensored". It is not GPT or Claude.

Is there a free tier?

New accounts get $0.50 trial credit. Top-ups start at $20.

What about refusals?

Refusals are rare. Errors are free.

Can I stream?

Yes. Use SSE.

How many tokens?

100k context. 16k output.

How this differs from a typical alternative

We serve one dedicated uncensored model, not a routed proxy. Typical alternatives hide model switching behind a single endpoint. Our API keeps it transparent. No embeddings. No fine-tuning. Just raw text generation. You know exactly what you are paying for. The billing is direct. No hidden tiers exist. We do not resell other vendors. You get predictable costs for high-volume workloads without subscription locks.

Feature	Typical Alternative	Ours
Model Source	Proxy or routed	Dedicated uncensored model
Output Types	Text, images, audio	Text only
Billing	Monthly subscriptions	Prepaid crypto credit

Use cases for the heretic uncensored model

The uncensored AI API enables reliable content generation without artificial filters for diverse creative and technical needs.

Adult Roleplay

Generate unrestricted narrative content with high fidelity using our dedicated uncensored LLM API, ensuring consistent character voice.

Multilingual Translation

Process twenty-two languages effectively, leveraging the model’s broad linguistic capabilities for accurate, uncensored text output.

Security Research

Analyze model behavior in low-refusal environments to identify edge cases without standard safety layer interference.

Who uses it, in which real situations; and plainly who it is NOT for

Developers building NSFW chatbots and adult content generators use our uncensored LLM API for unrestricted roleplay workflows. Creators rely on the 100,000-token context to maintain complex character personas without censorship refusals. This setup is NOT for teams needing image generation, audio processing, or embedding vectors. It is also unsuitable for users requiring multiple model routing, as we serve a single dedicated uncensored model.

Moving from another OpenAI-compatible provider in three steps

Update your base URL to HTTPS://api.hereticuncensored.com/v1, set your new API key, and send requests to the model id "uncensored". This single change routes traffic to our dedicated uncensored LLM API without altering your existing SDK logic. Verify connectivity by listing available models. Your prepaid credit activates immediately for high-volume NSFW API workflows.

Worked cost examples with token arithmetic that use only our prices

Your uncensored API API costs are predictable because we charge $0.15 per million input tokens and $0.50 per million output tokens. A typical 20k prompt plus 2k response costs exactly $0.007. Errors incur no fee. You top up via USDT or USDC on Base, receiving bonus credit for larger amounts. This transparent model ensures your prepaid balance lasts longer for high-volume NSFW workloads.

Common inquiries

What is heretic uncensored API?

It is a hosted, OpenAI-compatible chat-completions API. It serves one uncensored large language model for text generation. You send text in and receive text out via standard endpoints. The model is tuned to answer without content refusals for lawful adult use.

Does the uncensored LLM API support function calling?

Yes. The API supports function calling via tools and tool_choice parameters. You can also use JSON mode for structured outputs. Streaming via SSE is available, with token usage included in the final chunk. These features work within the 100,000 token context window.

How much does the uncensored AI API cost?

Input tokens cost $0.15 per 1M, and output tokens cost $0.50 per 1M. Credit is prepaid and charged by real usage. Errors and refusals are free. Paid credit never expires, and no monthly subscription fees apply to your account.

Can I use crypto for top-ups?

Yes, you can top up with USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is accepted. Bonus credit ranges from +5% to +15% based on your deposit size.

Is there a free trial for the uncensored AI online service?

Yes, every new account gets $0.50 of trial credit. This credit is valid for seven days from signup. The trial allows you to test the API before committing to a prepaid balance.

What are the rate limits for the uncensored LLM API?

You are limited to 300 requests per minute per key. You can have eight requests active simultaneously. The request body must be under 8 MB. One active key is allowed per account, and a new key replaces the old one.

Secure your API key

Get API key