Glossary

Every concept in this sheet, plus the smaller terms it uses. Select a concept to open its card.

Choosing a model: Providers offer tiers: large models for hard reasoning and coding, mid-size for most product work, small fast ones for classification and high volume.
Clear, structured instructions: State the task, the audience, the constraints and the output format explicitly, and separate instructions from data with headings or tags such as <document>.
Context window: The maximum number of tokens a model can take in one request, counting the system prompt, the conversation history, tool definitions, documents and the output.

Few-shot examples: Including a handful of example inputs and ideal outputs in the prompt so the model copies the pattern.

Keeping conversation state: Either resend the full history yourself each turn, or use a provider feature that keeps it for you where one exists.

Messages and roles: A conversation is a list of turns, each with a role: the user, and the model (called assistant, or model in Gemini).

Output limits and stop reasons: You cap output length, and each response says why it stopped: finished naturally, hit the limit, called a tool or was declined.

Reading token usage: Every response reports how many input and output tokens it used (and cached tokens, where relevant).
Reasoning and effort: Reasoning models think before answering, using extra hidden output tokens.

System prompts: Standing instructions that apply to the whole conversation: role, tone, rules, output format and context about the product.

Temperature and sampling: Temperature controls randomness when picking the next token: low values give focused, repeatable answers, higher values more varied ones.
The Responses API: OpenAI’s current main endpoint.
Tokens: Models read and write tokens: chunks of text that are often a word or part of one.

Your first request: Create a client (it reads the API key from an environment variable) and send a prompt.