context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
Why it matters
Reka Flash gains 128K context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → with interleaved text, image, video, and audio in one 21B model, and video input rises from one minute to three to five minutes. The update notes plainly that the model still cannot ground specific timestamps.
