API Reference

Base URL and Authentication

Use the dedicated base URL for all requests. Your API key authenticates via the Authorization header.

• Base URL: https://api.hereticuncensored.com/v1
• Model ID: uncensored

Retrieve your key from the dashboard. It is valid immediately upon creation.

Copycurl 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."}]
  }'

First Request

Send a simple chat completion to verify connectivity. The model responds without standard content filters for lawful adult use.

• Set model to uncensored.
• Include your messages array.

Check the response for choices containing your generated text.

Copyfrom 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)

Node SDK Integration

Initialize the client with your base URL and key. This ensures compatibility with standard OpenAI libraries.

• Install the official openai package.
• Pass baseURL and apiKey during initialization.

Call chat.completions.create() with your prompt. The response structure mirrors the standard API format.

Copyimport 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);

Streaming Responses

Enable real-time token delivery by setting stream to true. This reduces perceived latency for long outputs.

• Listen for delta chunks.
• Combine deltas to reconstruct the full response.

Token usage metadata appears in the final chunk. This is ideal for chat interfaces requiring instant feedback.

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 and Context

The API supports a 100,000-token context window. You can send up to 300 requests per minute per key.

• Max concurrent requests: 8
• Max output tokens: 16,000 (2,048 default)

Exceeding limits triggers a 429 error. Manage concurrency to maintain consistent throughput for high-volume workloads.

Error Handling and Codes

Handle errors gracefully to maintain application stability. Common codes include 401 for invalid keys and 402 for insufficient credit.

• 429 indicates rate limit exhaustion.
• 400 signals malformed request bodies.

Refunds are not issued for consumed tokens. Check your balance regularly to avoid service interruptions.