Grok jailbreak API Docs

Authentication and Base URL

Your API key authenticates every request. Send it as the Authorization header. The base URL is https://api.grokjailbreak.com/v1. Point your SDK client at this URL and use the key. No extra configuration needed.

Get your key on the Get API key page. Sign in with Google or use email and password. The key appears immediately. One key per account. A new key replaces the old one. Errors and refusals are free. Credit never expires. Privacy is simple. Only an email is required. Prompts are not used for training.

The /v1/chat/completions Endpoint

Send messages to POST /v1/chat/completions. Use the model ID uncensored. It is an open-weight model on our servers. Not a proxy for Grok, GPT, or others. It answers without content refusals for lawful adult use. Text in. Text out. Simple.

Supports temperature, top_p, stop, seed, presence_penalty, and frequency_penalty. Max output is 16,000 tokens. Default max_tokens is 2,048. Context window is 100,000 tokens total. The limit includes prompt plus completion. Request bodies must stay under 8 MB. Use the official SDKs or any compatible client.

Python SDK Quickstart

Use the official OpenAI Python library. Set the base URL to our endpoint. Inject your API key. Call chat.completions.create. Pass the uncensored model ID. The response contains the generated text. Handle errors gracefully. Network issues happen. Rate limits apply. Credit runs out. Check your balance.

This approach works for scripts, bots, and local apps. No special setup. Standard HTTP semantics. Streaming is supported via SSE. Token usage appears in the last chunk. Function calling is available. JSON mode is enabled. Stick to the parameters listed. Avoid unsupported features like embeddings or image generation.

Node.js SDK Integration

Initialize the OpenAI Node client. Configure the base URL. Provide your key. Call the completions endpoint. Receive the response text. The code mirrors the Python example. Consistency across languages matters. You can use this in serverless functions or Node services.

Handle async responses correctly. Await the result. Check for errors. The API returns standard HTTP status codes. 401 means invalid key. 402 means no credit. 429 means rate limit. Log these for debugging. Streaming works in Node too. Use the stream helper if available. Parse chunks carefully. Combine them for the final text.

Streaming and Token Usage

Enable streaming by setting stream: true. The API returns Server-Sent Events. Each chunk contains partial text. Token usage appears in the last chunk. This allows accurate counting. Use this for real-time displays. It reduces perceived latency. Users see results faster.

Parse the SSE format carefully. Handle incomplete chunks. Reassemble the text on the client or server. The model ID remains uncensored. Parameters like temperature still apply. Streaming does not change the context window limit. It stays at 100,000 tokens. Monitor usage to avoid surprises. Prepaid credit is charged by real token usage. Errors are free.

Rate Limits, Errors, and Context

Rate limits are strict. 300 requests per minute per key. 8 concurrent requests at the same time. Request bodies max 8 MB. Exceed these and you get 429. Invalid keys return 401. No credit returns 402. Handle these codes. Retry with backoff. Do not hammer the API.

The context window is 100,000 tokens. This includes prompt and completion. Max output is 16,000 tokens. Default is 2,048. Set max_tokens if needed. Content filtering is minimal. Only sexual content involving minors is refused. Everything else is allowed. Use this for research, creative writing, or adult content. No subscription. No monthly fee. Crypto top-up only. USDT or USDC. Bonus credits available. Start with trial credit. $0.50 for 7 days.

cURL

Copycurl https://api.grokjailbreak.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the cpu usage of my server"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.grokjailbreak.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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.grokjailbreak.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

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)