Developer Portal

Everything you need to integrate, build, and scale with EzenIA's AI capabilities.

Start Integrating SDK & Tools

API Integration Guide

AUTH

Authentication

curl -X POST "https://api.ezenia.com/auth/token" \
  -H "Content-Type: application/json" \
  -d '{
    "client_id": "your_client_id",
    "client_secret": "your_secret"
}'

This endpoint returns your access token, which needs to be included in all API requests in the Authorization header.

SDK

JavaScript SDK

npm install ezenia-sdk 
import { EzenClient } from 'ezenia-sdk'

const client = new EzenClient({
  apiKey: 'your-api-key',
  endpoint: 'https://api.ezenia.com'
})

// Make a request
client.models.list().then(console.log)
🧠

AI Models

GET /api/v1/models

Public
{ "models": [ { "id": "llm-001", "name": "Ezen-12B", "description": "General purpose language model" } ] }
âš¡

Stream Inference

POST /api/v1/session/{id}/stream

Protected
{ "input": "Explain quantum computing" }
{ "response": "Quantum computing uses qubits that...", "tokens_used": 357 }

API Rate Limits

12,000

Requests/minute

60,000

Tokens/minute

24,000

Images/minute

Frequently Asked Questions

How do I get an API key?

Access your API key from your organization's dashboard in the developer portal. Need one? Request access

How are charges calculated?

Our pay-as-you-go model charges based on tokens processed and API requests. Contact sales for enterprise pricing options or request a custom quote.

What models are available?

We offer 3 models for text generation, code execution, and image analysis. View API endpoints or list models using the /api/v1/models endpoint.