Heretic LLM: API Documentation

Base URL and Authentication

To begin using the Heretic LLM API, point your OpenAI-compatible client to our base URL: https://api.hereticllm.com/v1. The API uses standard Bearer token authentication. You can generate an API key by signing up with just an email and password on the Get API Key page. The key is displayed immediately after signup and can be regenerated at any time, which invalidates the previous key.

Set the OPENAI_API_KEY environment variable or pass the key directly in your client configuration. Ensure your base URL is updated to the Heretic endpoint. This setup allows you to use the official OpenAI SDKs with zero code changes, simply by swapping the base URL and key.

First Request

Make your first request to the chat completions endpoint. The model identifier is uncensored. This open-weight model is tuned to answer without content refusals for lawful adult use, making it ideal for uncensored coding, creative writing, or research. The context window supports up to 100,000 tokens for both prompt and completion combined.

Below is a basic cURL example to test the endpoint. Replace YOUR_API_KEY with your actual key.

The response will be a standard OpenAI-format object containing the generated text.

Copycurl https://api.hereticllm.com/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."}]
  }'

Python SDK Integration

Integrate the API into your Python applications using the official openai package. The library handles JSON serialization and streaming automatically. Initialize the client with your API key and the correct base URL. Then, call chat.completions.create with the model ID uncensored.

This approach works seamlessly for both synchronous and asynchronous workflows. The model responds to standard prompts, function calling, and streaming parameters just like other OpenAI-compatible endpoints. You can pass system prompts to guide the model's behavior or use user messages for direct interaction.

Copyfrom openai import OpenAI

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

Node.js SDK Integration

For JavaScript and TypeScript projects, use the openai npm package. Configure the client with the Heretic base URL and your API key. The API supports standard request structures, including tool definitions and function calling.

Make sure to handle the response correctly, especially when using async/await patterns. The model returns text responses that can be processed directly in your application logic. This integration is ideal for building chat interfaces, automated agents, or data processing pipelines that require uncensored LLM capabilities.

Copyimport OpenAI from "openai";

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

Streaming Responses

Enable real-time responses by enabling streaming in your API request. Set the stream parameter to true. The API will return a Server-Sent Events (SSE) stream containing chunks of text as they are generated. This reduces perceived latency and provides a smoother user experience for chat applications.

Each chunk in the stream contains a portion of the response. Handle these chunks incrementally to update your UI in real time. The streaming feature is fully compatible with the OpenAI SDKs, so you can use the standard stream iterators or event listeners to process the data efficiently.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Rate Limits, Errors, and Context

The API enforces a limit of 300 requests per minute per key and an 8 MB request body size. If you exceed the rate limit, you will receive a 429 error. Authentication errors return a 401 status, indicating an invalid or missing API key. If your prepaid credit is exhausted, the API returns a 402 error, requiring a top-up.

Credit never expires, and you can top up from $10 using crypto (USDT or USDC), with bonus credits for larger deposits. The model supports a 100,000-token context window. Ensure your prompts and completions fit within this limit. For more details on pricing and limits, visit the Pricing page.