Uncensored API
Heretic llm: The Uncensored API for Developers
Get the uncensored LLM endpoint with a 100k context window. Pay prepaid token rates via crypto. No subscriptions. No hidden fees. Start generating now.
- 100k context window
- Prepaid crypto only
- OpenAI compatible
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
No recurring billing. Prepaid credits do not expire.
Test with one call
curl https://api.llmheretic.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "summarize the main arguments in the attached pdf"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.llmheretic.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.llmheretic.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
Use your existing OpenAI SDKs by simply changing the base URL to our endpoint.
100k Context
Process massive documents with a 100,000 token context window for deep RAG applications.
Crypto Billing
Top up with USDT or USDC. Credits never expire.
No Subscriptions
Pay only for tokens used. Errors are free. No monthly recurring fees.
Streaming Support
Get real-time token streams via SSE with usage data in the final chunk.
Raw Output
Receive unfiltered text for adult, controversial, or technical topics without content refusals.
Setup process
Create Account
Sign up with Google or email to get your API key instantly.
Top Up Credit
Add crypto credits starting at $20 to begin using the uncensored LLM.
Start Generating
Send requests to the chat completions endpoint and receive raw text output.
Common applications
Large Document RAG
Index thousands of pages and retrieve answers using the full 100k context window.
Uncensored Chatbots
Build NSFW or unrestricted chat interfaces without worrying about standard content filters.
Raw Data Extraction
Extract structured JSON or raw text from noisy inputs without formatting refusals.
Dev Testing
Test your integrations with a standard OpenAI compatible API using prepaid credits.
Concrete Differences: No Routing, Pure Uncensored Output
Concrete Differences: No Routing, Pure Uncensored Output
We deliver exactly what you ask for. Our API serves a single, powerful uncensored large language model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or Gemini.
| Feature | Our Service | Typical Alternatives |
|---|---|---|
| Model Selection | One dedicated uncensored model | Multi-model routing gateways |
| Refusals | Minimal for adult content | Frequent safety filters |
| Billing | Strictly prepaid crypto | Monthly subscriptions |
| Complexity | Direct endpoint access | Complex routing layers |
| Context Window | 100,000 tokens | Variable limits |
| Output Limit | 16,000 tokens per request | Often restricted |
Worked Cost Examples: Token Arithmetic & Billing
Costs scale linearly with token usage at transparent rates. Input tokens cost $0.15 per million, while output tokens are $0.50 per million. Errors and refusals incur zero charges, ensuring you pay only for successful generation. For example, a 10k input and 2k output request totals approximately $0.002. Prepaid credit never expires, allowing you to budget precisely without monthly subscription fees or hidden costs.
Use Cases for heretic LLM: Raw Generation & RAG
The heretic LLM API powers raw text generation and RAG pipelines by processing large context windows without content refusals.
Epstein Document Analysis
Index 25,000+ files into a RAG system. Use the 100k context window to connect names, dates, and flight logs with reasoning, not just keywords.
Uncensored Fiction
Generate adult themes freely. The model answers without puritanical filters, allowing direct output for lawful creative writing.
Security Research
Test jailbreaks and boundary cases. Get unfiltered responses to controversial prompts without extra routing costs.
Who It Is For (And Who Should Look Elsewhere)
Developers needing pure, uncensored text generation for RAG pipelines or raw creative writing should use this API.
- Builders indexing massive document sets like the 25,303 Epstein files.
- Teams requiring a 100k context window for long-form coherence.
It is not for you if you need image generation, embeddings, or multi-model routing. We serve one open-weight model with a 16,000 token output limit via standard OpenAI-compatible endpoints.
Developer FAQs: Memory, Latency, and Integration
The Heretic LLM API supports a 100k context window, allowing you to process massive datasets like the Epstein files without losing thread.
- Latency: Expect 30–70 seconds for complex reasoning tasks, as this is a powerful 120B parameter model.
- Integration: Use the standard
/v1/chat/completionsendpoint; it works with any OpenAI-compatible SDK by simply changing the base URL. - Cost: Billing is strictly token-based, so you pay only for what you use, with no hidden subscription fees.
Integration Guide: From Signup to First Token
Access the uncensored API in five simple steps.
- Sign up via Google or email to receive your API key instantly.
- Top up your prepaid balance using USDT or USDC with no card required.
- Point your OpenAI-compatible SDK to
https://api.llmheretic.com/v1. - Send a
POSTrequest to/v1/chat/completionswith modeluncensored. - Receive raw, unfiltered text output directly in your application.
Common questions
What is the heretic LLM model and how does it differ from standard APIs?
It is a single uncensored large language model designed for raw text generation without content refusals. Unlike multi-model routers, it serves one consistent endpoint for unrestricted output, ensuring predictable behavior for NSFW or controversial topics without hidden routing logic.
How does prepaid billing work with crypto top-ups?
You pay strictly by token usage with no monthly fees. Credit never expires, so you can top up with USDT or USDC anytime. Errors and refusals do not consume your balance, ensuring you only pay for actual completed responses.
Can I use this API for RAG systems with large documents?
Yes, the model supports a 100,000 token context window for both prompt and completion. This allows indexing extensive document sets like thousands of files into a single conversation, enabling complex reasoning over large datasets without losing earlier context.
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.
What are the rate limits for a single API key?
Each key allows 300 requests per minute and eight concurrent connections. The request body is limited to eight megabytes. These limits ensure stable performance for high-throughput applications while preventing resource exhaustion during peak usage periods across the network.
Does the service store my prompts for training data?
No, your prompts are not used for training. Privacy is maintained by keeping your account tied only to an email address. Your data remains yours, allowing secure integration into proprietary workflows without worrying about third-party model improvement pipelines.
Access your API key instantly
Sign up, copy the key, update your endpoint URL. Simple configuration.
