Introduction

Welcome to AI API! This guide will help you get started with our OpenAI-compatible API that provides access to powerful AI models for chat completions, image analysis, and more.

What is AI API?

AI API is a high-performance, OpenAI-compatible API service that allows you to integrate advanced AI capabilities into your applications. Our API provides:

Chat Completions: Generate conversational responses
Vision Support: Analyze and describe images
Streaming Responses: Real-time response streaming
Auto Model Selection: Intelligent routing to the best available model

API Base URL

All API requests should be made to:

https://api.akbxr.com/v1

OpenAI Compatibility

Our API is fully compatible with the OpenAI SDK and API format. This means:

You can use existing OpenAI SDKs (JavaScript, Python, etc.)
No code changes needed for basic chat completions
Same request/response format as OpenAI
Drop-in replacement for OpenAI in most applications

Authentication

To authenticate your requests, include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Request Headers

To customize your requests, you can include additional headers:

Content-Type: application/json

Quick Example

Here's a simple example to get you started:

curl -X POST https://api.akbxr.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello, AI!"}],
    "stream": false
  }'

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.akbxr.com/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  messages: [{ role: "user", content: "Hello, AI!" }],
  model: "auto",
});

console.log(completion.choices[0].message.content);

import openai

openai.api_key = "YOUR_API_KEY"
openai.api_base = "https://api.akbxr.com/v1"

response = openai.ChatCompletion.create(
  model="auto",
  messages=[{"role": "user", "content": "Hello, AI!"}]
)

print(response.choices[0].message.content)