OpenAI - Docs | Transactional

Overview

AI Gateway provides full support for OpenAI's GPT models, including GPT-4o, GPT-4-turbo, o1, and GPT-3.5-turbo. All OpenAI features are supported including streaming, function calling, and vision.

Supported Models

Model	Context Window	Max Output	Best For
`gpt-4o`	128K	16K	General purpose, best quality
`gpt-4o-mini`	128K	16K	Fast, cost-effective
`gpt-4-turbo`	128K	4K	Complex reasoning
`o1`	200K	100K	Advanced reasoning
`o1-mini`	128K	65K	Fast reasoning
`gpt-3.5-turbo`	16K	4K	Simple tasks, lowest cost

Setup

1. Get OpenAI API Key

Go to OpenAI Platform
Create a new API key
Copy the key (starts with sk-)

2. Add Key to AI Gateway

Navigate to AI Gateway Settings
Click Add Key under Provider Keys
Select "OpenAI"
Paste your API key
Click Save

Usage

Basic Chat Completion

import OpenAI from 'openai';
 
const openai = new OpenAI({
  baseURL: 'https://api.transactional.dev/ai/v1',
  apiKey: process.env.GATEWAY_API_KEY,
});
 
const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' }
  ],
});

With Streaming

const stream = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true,
});
 
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

With Function Calling

const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What is the weather in Paris?' }],
  tools: [
    {
      type: 'function',
      function: {
        name: 'get_weather',
        description: 'Get the current weather for a location',
        parameters: {
          type: 'object',
          properties: {
            location: { type: 'string', description: 'City name' }
          },
          required: ['location']
        }
      }
    }
  ],
});

With Vision (GPT-4o)

const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'What is in this image?' },
        {
          type: 'image_url',
          image_url: { url: 'https://example.com/image.jpg' }
        }
      ]
    }
  ],
});

With JSON Mode

const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You output JSON.' },
    { role: 'user', content: 'List 3 fruits' }
  ],
  response_format: { type: 'json_object' },
});

Parameters

All standard OpenAI parameters are supported:

Parameter	Type	Description
`model`	string	Model ID (required)
`messages`	array	Chat messages (required)
`temperature`	number	Sampling temperature (0-2)
`max_tokens`	number	Maximum tokens to generate
`top_p`	number	Nucleus sampling parameter
`frequency_penalty`	number	Frequency penalty (-2 to 2)
`presence_penalty`	number	Presence penalty (-2 to 2)
`stop`	string/array	Stop sequences
`stream`	boolean	Enable streaming
`tools`	array	Function definitions
`tool_choice`	string/object	Tool selection mode
`response_format`	object	JSON mode

Pricing

AI Gateway passes through OpenAI's pricing. Current rates (as of Jan 2025):

Model	Input	Output
gpt-4o	$2.50/1M	$10.00/1M
gpt-4o-mini	$0.15/1M	$0.60/1M
gpt-4-turbo	$10.00/1M	$30.00/1M
o1	$15.00/1M	$60.00/1M
gpt-3.5-turbo	$0.50/1M	$1.50/1M

Migration from Direct OpenAI

Migrating is simple - just change two lines:

// Before
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});
 
// After
const openai = new OpenAI({
  baseURL: 'https://api.transactional.dev/ai/v1',
  apiKey: process.env.GATEWAY_API_KEY,
});
 
// All your existing code works unchanged!

Troubleshooting

Model not found

Ensure you've added your OpenAI API key in Settings.

Rate limits

OpenAI rate limits are passed through. Check your OpenAI account limits.

Invalid API key

Verify your OpenAI key is valid and has sufficient credits.

Next Steps

Anthropic Integration
Caching - Cache OpenAI responses
Fallback - Fall back to other providers