OpenAI

Configuration

Variable	Required
OPENAI_API_KEY	Yes

Usage

Gateway

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

Library

use llmg_providers::openai::OpenAiClient;
use llmg_core::provider::Provider;

let client = OpenAiClient::from_env()?;
// or
let client = OpenAiClient::new("sk-...");

Features

• Chat completions
• Embeddings
• SSE streaming
• Custom base URL (for proxies)