INFEREXAI DOCS

What is InferexAI?

InferexAI is an OpenAI-compatible LLM gateway that lets you call multiple AI providers through a single endpoint. You get a prepaid wallet, per-request usage tracking, and secure API key management — so you can ship faster without building infrastructure.

Quickstart

Make your first request in 2 minutes

API Reference

Full endpoint docs + live playground

Authentication

How to create and use API keys

Billing

Wallet top-up and usage tracking

How it works

InferexAI sits between your application and AI providers. Your code sends requests to https://inferexapi.cloudvoice.in/v1 using the standard OpenAI SDK. InferexAI authenticates the request, deducts cost from your wallet, routes to the best available provider, and returns the response.

Your App

→

InferexAI

→

Simplismart / OpenAI / Groq

Features

OpenAI-compatible

Drop-in replacement — change one line to switch from OpenAI.

Multi-provider routing

Route to Simplismart, OpenAI, Anthropic, or Groq with fallback.

Prepaid wallet

Top up with Razorpay. Pay only for what you use, no invoices.

Usage analytics

Per-request token counts, latency, and cost in real time.

Secure API keys

JWT-signed keys with revocation, rate limiting, and CORS controls.

Base URL

https://inferexapi.cloudvoice.in/v1

All API endpoints are relative to this base URL and are fully compatible with the OpenAI SDK.

Next: Quickstart