What is the context window size?

The context window supports 100,000 tokens for both input and output combined. You can generate up to 16,000 tokens in a single response. This allows for long documents or extended conversations without hitting hard limits quickly.

How do I handle errors?

Use standard HTTP status codes to manage flow. A 401 error means your API key is invalid or missing. A 402 error indicates insufficient prepaid credit. A 429 error signals that you have exceeded the 300 requests per minute limit. Implement retry logic with exponential backoff for rate limits.

Does the API support streaming?

Yes, streaming is fully supported via Server-Sent Events. Set the stream parameter to true to receive tokens in real-time. The final chunk includes usage statistics for billing. This feature reduces latency and improves user experience for chat applications.

API-Dokumentation — OpenAI-kompatible Endpunkte

Authentication & Base URL

Start by generating your key on the dashboard. Our service uses standard Bearer token authentication, so you only need to pass your key in the Authorization header. The base URL is https://api.isgrokunfiltered.com/v1. This URL works with any OpenAI-compatible SDK, meaning you can swap your existing client configuration without changing your code logic. Your key grants access to all features described here.

First Request

Send a simple text completion to verify your setup. Use the uncensored model ID for our raw inference engine. The following example demonstrates a basic POST request with system instructions.

curl https://api.isgrokunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of five unique Python script ideas."}]
  }'

This request returns a complete text response. You can adjust the max_tokens parameter to control output length. If the key is invalid, you will receive a 401 error. If you lack credit, you will see a 402 error.

Python SDK Integration

Use the official OpenAI Python library for easy integration. Point the client to our base URL and provide your key. The following snippet shows how to initialize the client and send a message.

from openai import OpenAI

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

This code handles the API call synchronously. You can iterate over the choices to extract the generated text. The library manages tokenization and retry logic automatically. Remember that our model supports up to 100,000 tokens in the context window.

Node SDK Integration

Integrate with Node.js using the standard OpenAI package. Set the basePath to our API endpoint. The following example demonstrates a basic chat completion call.

import OpenAI from "openai";

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

This approach works for both server-side and edge functions. You can parse the response content directly from the message object. Ensure you handle potential network errors gracefully. Our API returns standard JSON responses compatible with most JavaScript frameworks.

Streaming Responses

Enable streaming for lower latency and real-time token display. Set the stream parameter to true in your request. The API sends a series of Server-Sent Events (SSE) chunks.

stream = 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)

Each chunk contains partial text data. You can accumulate these tokens to build the final response. The last chunk includes the total token usage for billing. This method is ideal for chat interfaces where users expect immediate feedback. It reduces the perceived wait time significantly.

Limits & Context Window

Understand the constraints before scaling your application. You are allowed 300 requests per minute per key. You can have up to 8 concurrent requests at the same time. The request body must not exceed 8 MB. Your context window supports 100,000 tokens total, including both prompt and completion. Max output is 16,000 tokens per request, or 2,048 if you do not set max_tokens. If you exceed the rate limit, you will receive a 429 error. Credit is charged only for successful token usage, not for errors.

API Documentation