A million-token multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → model pitched at coding and multi-step tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition →, addressable from the AI SDK as alibaba/qwen3.8-flash and selectable inside Claude Code, Codex or Cursor at no-markup pricing.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
