What is the context window size?

The context window is 100,000 tokens for prompt and completion combined. You can output up to 16,000 tokens per request. If you do not set max_tokens, the limit is 2,048 tokens. This is enough for most long-form generation tasks. You can process large documents efficiently. The system handles context gracefully. No complex configuration is needed. Just send your prompt and get the result. The API is designed for performance. It scales with your needs. You do not need to manage chunking manually. The system handles it for you. This saves you time and effort. You can focus on building your application. The API is reliable and fast. No downtime during updates. Your code stays compatible with future changes. This is a robust solution for production apps.

How does pricing work?

You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. You only pay for actual token usage. Credit is prepaid and never expires. You can top up with USDT or USDC. Get bonus credit for larger amounts. Start building your application today. It is that simple. No monthly subscriptions. No hidden fees. Just transparent pricing. You know exactly what you pay. The system is designed for developers who value transparency. You do not need to manage complex billing cycles. Just top up with crypto and start sending requests. It is straightforward and reliable.

API Documentation | OpenAI Compatible Endpoint

Q: What happens if I hit the rate limit?

You get a 429 error if you exceed 300 requests per minute. Only 8 concurrent requests are allowed per key. Request body is limited to 8 MB. Invalid keys return a 401 error. No credit returns a 402 error. Errors are free. Refusals are free. You only pay for tokens sent and received. Context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Default max output is 2,048 tokens. Streaming sends token usage in the last chunk. Function calling is supported. JSON mode is supported. Temperature controls randomness. Top-p filters low probability tokens. Stop sequences halt generation early. Seed ensures reproducibility. Presence and frequency penalties adjust word usage. These parameters give you full control. You can tune the output precisely. The system is designed for developers who want simplicity. No complex billing cycles. Just prepaid credit. Top up with crypto. Get bonus credit for larger amounts. Start building your application today. It is that simple.

Base URL and Authentication

Connect using the standard OpenAI SDK configuration. Point your client to https://api.isgrokunrestricted.com/v1 and set your API key in the Authorization header. We support any whole number for your key and you get one active key per account. Your key appears immediately after signup. No phone number is required. We do not charge for errors or refusals. This means you only pay for actual token usage. Streaming sends token usage in the last chunk. You can track your balance via the dashboard. The system is designed for developers who want simplicity. You do not need to manage complex billing cycles. Just top up with crypto and start sending requests.

Make Your First Request

Send a POST request to the chat completions endpoint. Use the model ID uncensored for text generation. The base URL is HTTPS://api.isgrokunrestricted.com/v1. You can use any standard HTTP client. Here is a basic example using curl. It sends a simple prompt and expects a text response. This works with the official OpenAI SDKs too. Just change the base URL and API key. You do not need to install extra libraries for basic text. Streaming is supported via SSE. Function calling is also available. JSON mode works by setting the response format. Context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Errors are free. Refusals are free. You only pay for tokens sent and received. This makes testing cheap. You can experiment freely without worrying about unexpected bills. The system is transparent. No hidden fees. No monthly subscriptions. Just prepaid credit. Top up with USDT or USDC. Get bonus credit for larger amounts. Start building your application today. It is that simple.

curl https://api.isgrokunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain the architecture of the neural network"}]
  }'

Python SDK Integration

Install the official OpenAI Python package. Configure the client with our base URL and your API key. Set the model to uncensored. Send your prompt and get the response. This approach works for most use cases. You can handle errors gracefully. The SDK handles streaming automatically. You can also use function calling tools. Define your tools in the request. The model will return structured output. JSON mode ensures strict formatting. Use response_format to enforce it. Temperature controls randomness. Top-p filters low probability tokens. Stop sequences halt generation early. Seed ensures reproducibility. Presence and frequency penalties adjust word usage. These parameters give you full control. You can tune the output precisely. Streaming is efficient for long responses. It sends tokens as they are generated. This reduces perceived latency. Your users see text appearing in real time. Function calling enables complex workflows. You can integrate with external systems easily. The API is reliable and fast. No downtime during updates. Your code stays compatible with future changes. This is a robust solution for production apps.

from openai import OpenAI

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

Use the official OpenAI Node.js package. Set the base URL to our endpoint. Initialize the client with your API key. Call the chat completions endpoint. Pass the model ID uncensored. This works with any standard Node.js environment. You can handle async requests easily. The SDK manages the HTTP connections. Streaming is supported natively. You can process tokens as they arrive. Function calling is fully supported. Define tools and let the model decide. JSON mode ensures valid output. Use response_format for strict JSON. Temperature and top-p control creativity. Stop sequences define cutoff points. Seed provides deterministic results. Presence and frequency penalties adjust style. These tools help you fine-tune output. The API handles concurrency well. You can send multiple requests in parallel. Rate limits prevent abuse. You get 300 requests per minute. Only 8 concurrent requests per key. Request body is limited to 8 MB. This is enough for most use cases. If you need more, contact support. The system scales with your needs. No complex configuration required. Just install the package and go. It is straightforward and reliable.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.isgrokunrestricted.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 and Function Calling

Enable streaming by setting the stream parameter to true. The API returns chunks of text as they are generated. This reduces latency for users. You see output in real time. Function calling allows the model to invoke tools. Define tools in the request. The model returns a list of tool calls. You execute them and feed results back. This enables complex workflows. JSON mode ensures strict formatting. Use response_format to enforce it. The last chunk contains token usage. You can track your credit consumption. Streaming is efficient for long responses. It sends tokens as they are generated. This reduces perceived latency. Your users see text appearing in real time. Function calling enables complex workflows. You can integrate with external systems easily. The API is reliable and fast. No downtime during updates. Your code stays compatible with future changes. This is a robust solution for production apps. It handles errors gracefully. You can retry requests if needed. The system is designed for developers who value efficiency.

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)

Rate Limits and Constraints

You get 300 requests per minute per key. Only 8 concurrent requests are allowed. Request body is limited to 8 MB. If you exceed the limit, you get a 429 error. Invalid keys return a 401 error. No credit returns a 402 error. Errors are free. Refusals are free. You only pay for tokens sent and received. Context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Default max output is 2,048 tokens. Streaming sends token usage in the last chunk. Function calling is supported. JSON mode is supported. Temperature controls randomness. Top-p filters low probability tokens. Stop sequences halt generation early. Seed ensures reproducibility. Presence and frequency penalties adjust word usage. These parameters give you full control. You can tune the output precisely. The system is designed for developers who want simplicity. No complex billing cycles. Just prepaid credit. Top up with crypto. Get bonus credit for larger amounts. Start building your application today. It is that simple.

API Documentation