Google adds agentic video understanding to Gemini
Agentic video understanding is available for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite on the Interactions and GenerateContent APIs. Google says it can use up to 88% fewer tokens on long-form video than static processing.
- Context
- 1.05M
- Max output
- 65.54K
- Input price
- $0.75
- Knowledge cutoff
- Mar 2026
Source: Gemini API changelog, checked Sep 28, 2026. Summarized from the provider’s announcement.