/// API Documentation

One Endpoint. Full Power.

Everything you need to integrate MatrixAIBase into your application. Simple, fast, and well-documented.

[!]
Development Notice

MatrixAIBase API is currently under development. Documentation below represents the planned API specification. Join the waitlist to get early access.

# Quick Start

Get up and running with MatrixAIBase in under 5 minutes.

Base URL

Endpoint 
https://api.matrixaibase.com/v1

Authentication

All API requests require an API key passed in the Authorization header:

Header 
Authorization: Bearer YOUR_API_KEY

Your First Request

cURL 
curl -X POST https://api.matrixaibase.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "matrix-core-1",
    "messages": [
      {
        "role": "user",
        "content": "Hello, MatrixAIBase!"
      }
    ],
    "max_tokens": 256
  }'

Response

JSON Response 
{
  "id": "mx-abc123",
  "object": "chat.completion",
  "created": 1709500000,
  "model": "matrix-core-1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm MatrixAIBase. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 15,
    "total_tokens": 27
  }
}

# Models

MatrixAIBase offers three models optimized for different use cases.

Model Description Max Tokens Price per 1K tokens
matrix-core-1 Standard model. Balanced speed and quality. 4,096 $0.0003
matrix-core-1-fast Optimized for speed. Faster response times. 4,096 $0.0006
matrix-core-1-deep Enhanced reasoning. Best for complex tasks. 8,192 $0.0012

# SDKs

Official SDKs for popular languages. Install and start building in seconds.

Python

Installation 
pip install matrixaibase
Python Usage 
from matrixaibase import MatrixAI

client = MatrixAI(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="matrix-core-1",
    messages=[
        {"role": "user", "content": "Hello, MatrixAIBase!"}
    ]
)

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

Node.js

Installation 
npm install matrixaibase
JavaScript Usage 
import MatrixAI from 'matrixaibase';

const client = new MatrixAI({ apiKey: 'YOUR_API_KEY' });

const response = await client.chat.completions.create({
    model: 'matrix-core-1',
    messages: [
        { role: 'user', content: 'Hello, MatrixAIBase!' }
    ]
});

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

PHP

Installation 
composer require matrixaibase/sdk
PHP Usage 
use MatrixAIBase\Client;

$client = new Client('YOUR_API_KEY');

$response = $client->chat()->completions()->create([
    'model' => 'matrix-core-1',
    'messages' => [
        ['role' => 'user', 'content' => 'Hello, MatrixAIBase!']
    ]
]);

echo $response->choices[0]->message->content;

# API Reference

POST /v1/chat/completions

Creates a chat completion for the given messages.

Request Body

Parameter Type Required Description
model string Yes Model ID to use (e.g., "matrix-core-1")
messages array Yes Array of message objects with role and content
max_tokens integer No Maximum tokens to generate (default: 1024)
temperature float No Sampling temperature 0-2 (default: 0.7)
stream boolean No Enable streaming responses (default: false)
top_p float No Nucleus sampling parameter (default: 1.0)

Error Codes

Code Description
400 Bad request -- invalid parameters
401 Unauthorized -- invalid or missing API key
429 Rate limited -- too many requests
500 Internal server error

# Rate Limits

Rate limits vary by plan to ensure fair usage for all users.

Plan Requests/min Tokens/min
Basic 20 10,000
Standard 60 50,000
Scale Custom Custom

Rate limit headers are included in every response:

Response Headers 
X-RateLimit-Limit: 60
X-RateLimit-Remaining: 58
X-RateLimit-Reset: 1709500060

# Support

Need help? We're here for you.