GPT-4o

Most capable multimodal model with vision and audio capabilities

Context Window128K

Max Output16K

Input Price$2.5/1M

Output Price$10/1M

Cached Input$1.25/1M

CAPABILITIES

What This Model Can Do

Chat Completions

Multi-turn conversations with context

Vision

Analyze and understand images

Function Calling

Call external functions and APIs

JSON Mode

Guaranteed valid JSON output

Streaming

Real-time response streaming

System Prompt

Custom system instructions

CODE

Quick Start

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.transactional.dev/ai/v1',
  apiKey: process.env.GATEWAY_API_KEY, // gw_sk_...
});
const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain quantum computing in simple terms.' }
  ],
  temperature: 0.7,
  max_tokens: 1024,
});
console.log(response.choices[0].message.content);

YOUR AGENTS DESERVE
REAL INFRASTRUCTURE.

START BUILDING AGENTS THAT DO REAL WORK.

Deploy Your First Agent