Fomoa AI2.0

API Documentation

T4 GPU Powered

Integrate Fomoa AI 2.0 into your applications with our OpenAI-compatible API. Powered by NVIDIA T4 GPU for ~3 second response times.

T4 GPU
~3s Response
Vision
Voice Input
Text-to-Speech
PPT Generation
Hindi Support

Introduction

The Fomoa AI 2.0 API provides access to our powerful GPU-accelerated vision-language model. Powered by NVIDIA T4 GPU, enjoy blazing fast ~3 second response times. Our API is fully compatible with the OpenAI Chat Completions API format, making it easy to integrate with existing applications and SDKs.

~3s
Response Time
T4 GPU
Acceleration
128K
Context Window
$0.50
Per Million Tokens

Key Features

  • GPU-Accelerated - NVIDIA T4 GPU for ~3 second inference
  • Vision Capabilities - Analyze images, documents, and screenshots
  • Voice Input - Built-in speech recognition (Web Speech API)
  • Text-to-Speech - Listen to AI responses read aloud
  • PPT Generation - Create professional presentations via API
  • Hindi Support - Full Hindi language understanding
  • Streaming - Real-time streaming responses
  • OpenAI Compatible - Drop-in replacement for OpenAI SDK

Base URL

https://fomoa.cloud/api/v1

Quick Start

curl https://fomoa.cloud/api/v1/chat \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "fomoa-vision-2.0",
    "messages": [
      {"role": "user", "content": "Hello, who are you?"}
    ]
  }'

What's New in Fomoa AI 2.0

NVIDIA T4 GPU

Inference powered by 16GB VRAM GPU

Voice Commands

Speak to chat with voice recognition

Text-to-Speech

Listen to AI responses read aloud

PPT Generation

Create presentations via API

Hindi Language

Full Hindi language support

~3s Response

Lightning fast GPU inference