API Documentation & Quickstart

Base URL & Authentication

Our API lives at https://api.llmjailbreak.cc/v1 and accepts standard headers. You need an Authorization: Bearer <your-api-key> header on every request. Get your key instantly via the dashboard using Google or email, then paste it into your client. The base URL ensures compatibility with existing OpenAI SDKs without code changes.

Copycurl https://api.llmjailbreak.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "explain the Krebs cycle"}]
  }'

If the key is missing or invalid, the API returns a 401 error immediately. Check the dashboard if you suspect a typo. No phone number is required for signup.

POST /v1/chat/completions Explained

Send text data to the /v1/chat/completions endpoint to get responses. This is the primary interaction point for the uncensored model. You define the model as uncensored and provide a messages array. The API processes the prompt and returns generated text.

Copyfrom openai import OpenAI

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

Keep your payloads under 8 MB. The system supports a 100,000 token context window combining prompt and completion. If you exceed limits, the API rejects the request. Use this endpoint for NSFW roleplay or security research without content filters.

Parameters: Temperature, Top-P, and Seed

Control creativity with temperature and diversity with top_p. Set seed for deterministic outputs during testing. These parameters behave exactly like their OpenAI counterparts. Adjust them to fine-tune the model's behavior for your specific use case.

Copyimport OpenAI from "openai";

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

Higher temperature values increase randomness. Lower values make responses more predictable. The seed parameter ensures reproducibility. Use these tools to calibrate the model for creative writing or precise data extraction tasks.

JSON Mode & Function Calling

Enforce structured output using response_format: {"type": "json_object"}. This ensures the model returns valid JSON. You can also use function calling to integrate with external tools. Define functions in the tools array and let the model decide when to call them.

Function calling supports tool_choice for strict enforcement. Use this for agents or data pipelines. The API handles the routing automatically. No extra configuration is needed beyond standard OpenAI JSON mode.

Streaming Responses (SSE)

Stream responses using Server-Sent Events (SSE). This reduces latency for long outputs. The API sends tokens incrementally. You can process them in real-time. This is ideal for chat interfaces or live demonstrations.

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)

Token usage statistics appear in the final chunk. Monitor this for billing accuracy. Streaming does not affect pricing. Each token is billed separately at the standard rate. Use this for a smoother user experience.

Rate Limits & Quotas

Expect 429 errors if you exceed 300 requests per minute per key. Concurrent requests are limited to 8 per key. These limits prevent abuse and ensure stability. Upgrade your plan or wait if you hit the cap.

A 402 error indicates insufficient credit. Top up with crypto to continue. Credit never expires. Errors and refusals are free. Monitor your usage via the dashboard. The API key is unique per account. Replace it if needed.