SYSTEM 03/14 · THE FIELD GUIDE
Working with LLM APIs
Calling Claude, GPT, and Gemini from code — streaming, structured outputs, function calling, caching, and the bill.
API Basics
Keys, messages, roles, and errors: everything before your first production call.
LLM APIsBEGINNERYour First API CallBEGINNERAPI ErrorsINTERMEDIATEChoosing a Model TierINTERMEDIATEAPI KeysBEGINNERAPI Data PrivacyBEGINNERThe Messages ArrayBEGINNERMulti-Turn ConversationsBEGINNERSDK vs Raw HTTPBEGINNERClaude vs GPT vs GeminiINTERMEDIATESampling ParametersINTERMEDIATEmax_tokens & TruncationBEGINNERCounting Tokens Pre-RequestINTERMEDIATEtiktokenINTERMEDIATE
Provider Guides
Hands-on first steps with every major door into the models.
Streaming & Structured Outputs
Tokens as they arrive, and JSON you can actually parse.
Streaming & SSEBEGINNERStructured OutputsINTERMEDIATEJSON Mode vs Structured vs FunctionsINTERMEDIATEParsing Stream EventsINTERMEDIATEStreaming Structured OutputADVANCEDStreaming vs Non-StreamingINTERMEDIATEMid-Stream ErrorsADVANCEDInstructor + PydanticINTERMEDIATEOutlinesINTERMEDIATEBAMLINTERMEDIATEZodINTERMEDIATE
Function Calling
The API mechanism that lets a model ask your code to do things.
Cost, Caching & Rate Limits
Token economics: what you pay, what you cache, what throttles you.