context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
Why it matters
GLM-5.3-Flash is now one model string away in the AI SDK, with a 1M-token context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → and vision input, and selectable inside Claude Code, Codex, Cursor and OpenCode through Gateway at provider pricing.
