API Documentation

Authentication and Base URL

Start every request by setting the base URL to https://api.deepseekjailbreakprompt.com/v1. You must include an Authorization header with your bearer token. This key is generated instantly after you sign up with Google or an email address. There are no monthly subscriptions or hidden fees, just prepaid credit that never expires.

First Request

Send a POST request to the chat completions endpoint to test connectivity. Use the model identifier uncensored to access our tuned model. The following curl command demonstrates the basic structure for a simple text query.

Copycurl https://api.deepseekjailbreakprompt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show the current server status"}]
  }'

If you receive a 401 error, your API key is invalid. A 402 error indicates insufficient credit, while a 429 response means you have exceeded the 300 requests per minute limit.

Python SDK Integration

Use the official OpenAI Python library to interact with our service. Set the base_url and api_key parameters before making any calls. This approach ensures compatibility with standard client code used for other providers.

Copyfrom openai import OpenAI

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

You can adjust parameters like temperature and top_p to control creativity. The model supports a context window of 100,000 tokens for both input and output combined.

Node SDK Usage

Install the openai package for Node.js and configure the client similarly to the Python example. Pass your API key and the correct base URL to initialize the instance.

Copyimport OpenAI from "openai";

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

Request a response using the uncensored model ID. You can specify max_tokens to limit output length, defaulting to 2,048 if omitted. The maximum output per request is 16,000 tokens.

Streaming Responses

Enable streaming by setting the stream parameter to true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage statistics are included in the final chunk of the stream.

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)

This method is ideal for applications requiring immediate partial results. You can handle errors or interruptions gracefully by checking the stream status.

Limits, Errors, and Context

Each API key is limited to 300 requests per minute and allows up to 8 concurrent requests. The maximum request body size is 8 MB. If you exceed these limits, you will receive a 429 status code. Errors like 401 indicate invalid authentication, while 402 signals a lack of credit.

The model supports a 100,000-token context window. This allows for extensive document processing or long conversation histories. Requests are charged based on actual token usage, with errors being free.