Guides
The Guides section answers “how do I…” questions. Each page focuses on a single capability: it shows the minimal working code, explains the key parameters, and points out any platform-specific behaviour you need to know about. All examples use the OpenAI-compatible API, so existing OpenAI SDK code usually works with a one-line base URL change.
By modality
Section titled “By modality” Chat completions System and user messages on the OpenAI-compatible Chat API.
Streaming Token-by-token responses via Server-Sent Events.
Image input Image input on the chat API.
Image generation Text prompts to images.
Audio Whisper transcription and translation.
Embeddings Vectors for search and RAG.
OCR Two models that turn documents into Markdown.
Reranking Sort search results by relevance to a query.
Features
Section titled “Features” Function calling Tools and JSON arguments.
Structured outputs JSON Schema on the Responses API.
Reasoning The reasoning_effort parameter, per model.
Decisions Typed answers for routing and checks.
Production
Section titled “Production” Prefix caching Reuse a repeated prompt prefix.
Errors and reliability Retries, status codes, and the queue.
Embeddings and RAG Embeddings and RAG.
Migrate from OpenAI Point an OpenAI SDK at this API.