Uncensored LLM API
Heretic project: The Uncensored LLM API
Drop-in, OpenAI-compatible API for uncensored generation with a 100,000 token context window, serving one dedicated model without routing overhead or data training.
- Prepaid crypto billing with no monthly fees
- Zero content refusals for lawful adult content
- Standard OpenAI endpoints with streaming support
Try with trial creditView documentation
Test with one call
curl https://api.hereticproject.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "list dependencies for node project"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.hereticproject.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.hereticproject.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);Capabilities
OpenAI Compatible
Works with official SDKs by changing base_url and API key.
Large Context
Supports 100,000 tokens for prompt and completion combined.
Streaming Support
Returns token usage details in the final SSE chunk.
Function Calling
Full support for tools and tool_choice parameters.
JSON Mode
Ensure structured output with response_format json_object.
Privacy First
Prompts are not used for training your data.
Setup process
Get Your Key
Sign up with Google or email to receive your key immediately.
Add Crypto Credit
Top up with USDT or USDC to start using the API.
Make a Request
Send a POST request to the chat-completions endpoint with your key.
Use cases
NSFW Roleplay
Generate uncensored creative writing without artificial content filters blocking adult themes.
Uncensored Coding
Get raw code outputs without refusals for unconventional or niche programming tasks.
Data Extraction
Process large documents using the 100k token context window for deep analysis.
Research Models
Test the uncensored model directly via API or download weights from HuggingFace.
Migrate your OpenAI or OpenRouter integration in three steps
Switch to the uncensored LLM API by updating your base URL and model ID. First, change your base URL to HTTPS://api.hereticproject.com/v1. Second, set the model parameter to 'uncensored'. Third, insert your prepaid API key. This works with standard OpenAI SDKs. You get 100,000 token context without proxy overhead. No subscriptions, just crypto billing.
What developers actually ask about uncensored APIs
What is the actual uncensored AI API for NSFW chatbot needs?
The Heretic API provides a single, uncensored model via the standard OpenAI-compatible endpoint. It eliminates proxy overhead by serving one tuned model that does not refuse lawful adult, fictional, or controversial topics. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid crypto billing ensures privacy without monthly subscriptions. This direct approach keeps costs low and transparency high for developers needing reliable, unfiltered generation.
heretic project: Use cases for uncensored generation
The heretic project API delivers unrestricted text generation for NSFW roleplay, creative writing, and unfiltered coding without content refusals.
NSFW Roleplay
Generate mature, adult-themed narratives without artificial guardrails blocking lawful content.
Creative Writing
Explore controversial themes or dark topics freely, ensuring your creative vision remains intact.
Uncensored AI Chatbot
Build chatbots that answer directly, skipping the typical polite refusals found in standard models.
Uncensored AI Model
Access a single, dedicated uncensored AI model optimized for direct, unfiltered responses.
Signs this is a true uncensored model, not a proxy
Our service runs one dedicated model, eliminating proxy routing overhead and vendor lock-in. You get direct access to an open-weight architecture tuned for unrestricted creative output. Unlike multi-vendor gateways, we offer predictable per-token billing without hidden markup. The API serves a single endpoint, ensuring consistent behavior for uncensored roleplay and coding tasks without complex configuration layers.
| Feature | Our Approach |
|---|---|
| Model Selection | Single, fixed uncensored model |
| Billing | Direct per-token crypto payments |
| Routing | No intermediate proxies |
| Transparency | Open weights, no trade secrets |
Common mistakes when integrating uncensored LLMs
Developers often assume uncensored means unlimited context, yet Heretic enforces a strict 100,000-token window. Others forget that the model requires explicit JSON mode for structured outputs, causing parsing failures. Using standard temperature settings may still yield refusals for borderline topics. Always verify your base_url points to api.hereticproject.com. Remember that prepaid crypto credits never expire, so budget errors are permanent unless you contact support.
From signup to first token: How it works
Start generating uncensored responses in under two minutes with this simple workflow.
- Visit the Get API key page and sign in via Google or email.
- Receive immediate access to your unique key and $0.50 trial credit.
- Configure your client by setting the base URL to
https://api.hereticproject.com/v1and your key. - Send a POST request to
/v1/chat/completionswith the model IDuncensored. - Receive streamed tokens instantly, free from standard content refusals.
Common questions
What is the heretic project API?
It is a hosted, OpenAI-compatible endpoint serving a single uncensored LLM. You send text in and get text out via POST /v1/chat/completions, with no model routing or proxy overhead required for integration.
Does it support streaming responses?
Yes, it supports Server-Sent Events. You receive token-by-token updates, with total usage stats included only in the final chunk of the stream, allowing for low-latency user experiences.
How much does the uncensored AI API cost?
Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free, and prepaid credit never expires, ensuring you only pay for actual usage.
Can I use my existing OpenAI SDK?
Yes, simply change the base URL to HTTPS://api.hereticproject.com/v1 and provide your API key. The model ID is "uncensored," making it a drop-in replacement for standard OpenAI-compatible clients.
What is the context window limit?
The model supports a 100,000-token context window for combined prompt and completion. Max output is 16,000 tokens per request, or 2,048 tokens if you do not explicitly set the max_tokens parameter.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Get your API key
Sign up, copy your key, update the base URL. That is all you need to do.
