Build step by step

Developer Tutorials

Hands-on Python and Node.js tutorials for chat, structured output, streaming, tool calling and production deployment.

Copy a working pattern, understand it and adapt it to your application.

Learn in the order developers build.

Start with the decision, move into implementation and finish with production checks.

Structured learning path

Make the first call

Configure the key, base URL, model and message.

Stream responses

Render partial output and handle interrupted requests.

Add structured output

Validate JSON and tool arguments before use.

Deploy

Protect keys, log requests and set production limits.

Build topical authority, not article islands.

Core guides

5 guided starting points

Python01

Python AI API Quickstart

Create a chat completion with an OpenAI-compatible SDK.

Open guide

Node.js02

Node.js AI API Quickstart

Build a server-side request and stream the response.

Open guide

Application pattern03

Structured Output Tutorial

Request and validate reliable JSON responses.

Open guide

Application pattern04

Tool Calling Tutorial

Connect model decisions to application functions.

Open guide

Deployment05

Deploy with Vercel AI SDK

Build a multi-model route for a production web app.

Open guide

Ship a streaming chat route

Start with a server-side model request, stream tokens to the UI and keep provider credentials out of the browser.

Server-only API key

Abort and timeout handling

Streaming UI state

Request and error logs

Turn the guide into a request.

Try a model in the Playground, then use the Quickstart to move the same pattern into Python or Node.js.

Try without coding Open Quickstart

Explore every growth topic.

AI API Guides

Go from model shortlist to a working production request.

LLM Infrastructure

Build an AI request layer that survives provider and model changes.

AI Agent

Move from a prompt demo to an observable agent workflow.

Cost Optimization

Lower cost without hiding quality or reliability trade-offs.

Model Comparison

Select a model based on the job, not the leaderboard headline.

Tutorials

Copy a working pattern, understand it and adapt it to your application.

Frequently asked questions

AEO-ready answers

Should AI API keys be used in browser code?

No. Keep provider credentials on the server and expose only your own authenticated application route to the browser.

Which SDK should a tutorial use?

Use an OpenAI-compatible SDK for portability or a provider-native SDK when the workflow needs provider-specific features.