← Back to Marketplace

OpenAI

Bearer

GPT-4o, DALL-E, Whisper, Embeddings. The most widely used AI API.

https://api.openai.com
OVERVIEW

OpenAI's API gives you access to the GPT family of large language models, DALL-E for image generation, Whisper for speech recognition, and text embedding models for semantic search. It's the most widely deployed AI API in production today.

The API follows a consistent REST pattern with JSON request/response bodies. Most endpoints accept a model parameter and return structured JSON. Streaming is supported via Server-Sent Events for chat completions and the Responses API.

GET YOUR API KEY

Authentication setup

  1. Go to platform.openai.com and sign in
  2. Navigate to API Keys in the left sidebar
  3. Click Create new secret key
  4. Give it a name and select a project
  5. Copy the key. It starts with sk-proj-
Token format sk-proj-...
Auth type bearer
QUICK CONNECT

Create a connection in one request.

CONNECT OPENAI
POST /connections Authorization: Bearer $TOKEN Content-Type: application/json { "name": "OpenAI", "base_url": "https://api.openai.com", "auth_type": "bearer", "auth_config": {"token": "sk-proj-..."} } → {"id": "cn_xxxxxxxx", "name": "OpenAI"}
KEY ENDPOINTS

What you can call via proxy.

MethodPathDescription
POST /v1/chat/completions Chat with GPT-4o, GPT-4o-mini, o1, o3
POST /v1/responses Responses API. Streaming, tools, web search
POST /v1/embeddings Generate text embeddings (text-embedding-3-small/large)
POST /v1/images/generations Generate images with DALL-E 3
POST /v1/audio/transcriptions Transcribe audio with Whisper
POST /v1/audio/speech Text-to-speech (tts-1, tts-1-hd)
GET /v1/models List all available models
POST /v1/moderations Content moderation. Flag harmful text
EXAMPLE

Chat Completion

PROXY CALL
POST /proxy/cn_xxxxxxxx/v1/chat/completions Authorization: Bearer $TOKEN Content-Type: application/json { "model": "gpt-4o", "messages": [ {"role": "user", "content": "Explain API proxies in one sentence."} ] } { "id": "chatcmpl-abc123", "choices": [{ "message": { "role": "assistant", "content": "An API proxy sits between your client and an upstream API, injecting credentials and logging requests so your application code never handles secrets directly." } }], "model": "gpt-4o", "usage": {"prompt_tokens": 14, "completion_tokens": 32} }
USE CASES

What people build with OpenAI.

Chatbots & Assistants

Build conversational AI with GPT-4o. Use tool calling to connect to external data.

Content Generation

Generate blog posts, product descriptions, emails, and marketing copy at scale.

Image Generation

Create images from text prompts with DALL-E 3 for design, marketing, and creative work.

Semantic Search

Embed documents and queries with text-embedding-3 for similarity search and RAG.

← Back to Marketplace Developer Guide →
# OpenAI > GPT-4o, DALL-E, Whisper, Embeddings. The most widely used AI API. ## Overview OpenAI's API gives you access to the GPT family of large language models, DALL-E for image generation, Whisper for speech recognition, and text embedding models for semantic search. It's the most widely deployed AI API in production today. The API follows a consistent REST pattern with JSON request/response bodies. Most endpoints accept a model parameter and return structured JSON. Streaming is supported via Server-Sent Events for chat completions and the Responses API. - **Base URL:** https://api.openai.com - **Auth type:** bearer - **Token format:** sk-proj-... ## Get Your API Key 1. Go to platform.openai.com and sign in 2. Navigate to API Keys in the left sidebar 3. Click Create new secret key 4. Give it a name and select a project 5. Copy the key. It starts with sk-proj- ## Quick Connect bashcurl -X POST https://api.liteio.dev/connections \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ -d '{ "name": "OpenAI", "base_url": "https://api.openai.com", "auth_type": "bearer", "auth_config": {"token": "sk-proj-..."} }' ## Key Endpoints MethodPathDescription POST/v1/chat/completionsChat with GPT-4o, GPT-4o-mini, o1, o3 POST/v1/responsesResponses API. Streaming, tools, web search POST/v1/embeddingsGenerate text embeddings (text-embedding-3-small/large) POST/v1/images/generationsGenerate images with DALL-E 3 POST/v1/audio/transcriptionsTranscribe audio with Whisper POST/v1/audio/speechText-to-speech (tts-1, tts-1-hd) GET/v1/modelsList all available models POST/v1/moderationsContent moderation. Flag harmful text ## Example: Chat Completion bashcurl -X POST https://api.liteio.dev/proxy/cn_xxx/v1/chat/completions \ -H "Authorization: Bearer $TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o", "messages": [ {"role": "user", "content": "Explain API proxies in one sentence."} ] }' ## Use Cases - **Chatbots & Assistants**: Build conversational AI with GPT-4o. Use tool calling to connect to external data. - **Content Generation**: Generate blog posts, product descriptions, emails, and marketing copy at scale. - **Image Generation**: Create images from text prompts with DALL-E 3 for design, marketing, and creative work. - **Semantic Search**: Embed documents and queries with text-embedding-3 for similarity search and RAG. ## Links - Back to Marketplace - Developer Guide - Get API Key