Complete reference for OpenAI's stateless APIs including Chat Completions, embeddings, images, audio, and moderation.

• Supports GPT-5 series (with reasoning_effort control), GPT-4o multimodal, o3 reasoning models, and legacy GPT-4 variants; streaming, function calling, and structured JSON outputs included
• Embeddings API for RAG with custom dimensions (256–3072), DALL-E 3 image generation, Whisper transcription, and TTS with 11 voices
• Batch API for 50% cost savings on large-scale processing; Realtime API for low-latency voice interactions via WebSocket
• Prevents 16 documented errors including model name mistakes (gpt-5.1-mini doesn't exist), reasoning_effort defaults in GPT-5.1/5.2, embedding dimension mismatches, and TypeScript null-check gotchas