Capability

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
$0.75Also priced under other conditions: Prompts over 200K tokens, Priority tier, Flex tier, Batch
Knowledge cutoff
Mar 2026

Gemini API changelog ↗

Source: Gemini API changelog, checked Sep 28, 2026. Summarized from the provider’s announcement.