openai-platform

Introduction

OpenAI provides a robust API platform that allows developers to integrate advanced AI models into their applications. This includes capabilities for text generation, embeddings, image generation, and more.

Core Capabilities

1. Chat Completions

The Chat Completions API is the primary way to interact with models like GPT-4o and GPT-4o-mini. It uses a message-based interface.

Endpoint: https://api.openai.com/v1/chat/completions

Basic Usage (Node.js):

const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" }
  ],
});

2. Embeddings

Embeddings are numerical representations of text that can be used for search, clustering, and recommendations.

Models: text-embedding-3-small, text-embedding-3-large

Basic Usage:

const embedding = await openai.embeddings.create({
  model: "text-embedding-3-small",
  input: "The food was delicious and the service was excellent.",
  encoding_format: "float",
});

3. Assistants API

The Assistants API allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries.

4. Image Generation (DALL·E)

Generate or edit images based on natural language prompts.

Model: dall-e-3

Models Comparison

Model	Description	Use Case
GPT-4o	High-intelligence flagship model	Complex tasks, reasoning
GPT-4o-mini	Fast, affordable small model	Simple tasks, high-volume
o1-preview	Reasoning model for complex problems	Science, math, coding

Pricing & Rate Limits

OpenAI uses a pay-as-you-go model based on tokens. Tokens can be thought of as pieces of words.

• Input Tokens: Tokens sent to the model.
• Output Tokens: Tokens generated by the model.

You can monitor your usage and set limits in the OpenAI Dashboard.

Integration Example: Continue.dev

To use OpenAI with Continue.dev, add the following to your config.json:

{
  "models": [
    {
      "title": "GPT-4o",
      "provider": "openai",
      "model": "gpt-4o",
      "apiKey": "YOUR_API_KEY"
    }
  ],
  "tabAutocompleteModel": {
    "title": "GPT-4o-mini",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "apiKey": "YOUR_API_KEY"
  }
}