OpenAI Chat Completions API
Send multi-turn messages; get assistant replies. Use **server-side** only.
Reference
API reference
Endpoint docs with examples — chat, embeddings, tools, and local runners.
19 docs
OpenAI Embeddings API
Turn text into vectors for semantic search and RAG.
OpenAI errors & rate limits
Production apps need retries, backoff, and clear user errors.
Anthropic Messages API
Send conversations to Claude models. Keys stay **server-side**.
OpenAI function calling
Let the model return **structured tool calls**; your server executes functions and sends results back.
Anthropic tool use
Let Claude request **tools** with structured inputs — your code executes and returns results.
Ollama local API
Run open-weight models on your machine; hit **localhost** from your app.
RAG retrieval pattern
Standard **embed → search → pack → generate** loop for question answering over your docs.
Google Gemini generateContent
Multimodal Google AI endpoint — text in, text out (images optional in newer models).
OpenAI structured outputs
Return **JSON matching a schema** — reliable parsing for agents and APIs.
OpenAI vision chat
Same **chat completions** endpoint with image parts in messages.
OpenAI Batch API
Run **large offline jobs** for embeddings or chat completions at lower cost — submit JSONL, poll status, download results within ~24h.
OpenAI fine-tuning & jobs
Train a **custom model variant** on your examples — tone, format, domain phrasing — via supervised fine-tuning jobs.
Anthropic streaming messages
Stream Claude replies **token-by-token** for faster perceived latency in chat UIs.
Gemini multimodal generateContent
Send **text, images, audio, or video** in one request; get text (or structured) output from Google Gemini models.
Whisper audio transcription
Convert **speech to text** with OpenAI Whisper (or compatible endpoints) — meetings, voice notes, accessibility, and RAG over audio.
Text-to-speech API
Turn **written text into spoken audio** — voice assistants, accessibility, podcasts, and in-app narration.
AWS Bedrock invoke model
Call **foundation models inside AWS** — Claude, Llama, Titan, and others — with IAM auth instead of vendor API keys in app code.
Azure OpenAI chat completions
Run **OpenAI-compatible chat** on Microsoft Azure — enterprise SSO, private networking, and regional deployment.