Skip to content
  • Tech Dev NotesTech Dev Notes
Apps
  • Lookup
  • Compare
Market movement
  • Charts
  • Rankings
Visual proof
  • Screens
  • Store listings
  • Icons
Stacks and releases
  • Tech stacks
  • Tool releases
  • Developers
More
  • X feature flags
  • Grokipedia
  • Grok companions
  • Blog
  • Follow on X
ChartsRankingsMoversCompareLookupScreensTech stacksReleases

© 2026 Tech Dev Notes

RSSAboutAPIStatusSecurityPrivacyTermsSitemap@techdevnotes
Gemini Docs

Google · Docs

Gemini Docs

September 1, 2026 at 6:03 PM UTC

Documented agentic video understanding on /gemini-api/docs/video-understanding and /gemini-api/docs/generate-content/video-understanding: for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash Lite, the model can dynamically navigate the timelin…

Changelog

Video understanding

  • Documented agentic video understanding on /gemini-api/docs/video-understanding and /gemini-api/docs/generate-content/video-understanding: for Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash Lite, the model can dynamically navigate the timeline and load only needed transcript, frames, and audio (vs default static 1 FPS processing), with guidance on when to choose each mode and how to set processing / media_processing.

Tokens

  • Clarified video token rates on /gemini-api/docs/tokens and /gemini-api/docs/generate-content/tokens: the fixed per-second rate applies to static processing; added a Video token usage by processing mode section covering static vs agentic calculation, typical savings on long-form content, and where agentic tokens appear in usage metadata.

Media resolution

  • On /gemini-api/docs/media-resolution and /gemini-api/docs/generate-content/media-resolution, explained how media_resolution (tokens per frame) relates to processing / media_processing (what content is loaded), including that both can be set together.

Optimization & pricing

  • On /gemini-api/docs/optimization, added guidance to reduce long-form video input costs with agentic processing (up to 88% fewer input tokens), including API parameter names and when static may still be preferable for short, latency-sensitive clips.
  • On /gemini-api/docs/pricing, noted that agentic video understanding bills from variable tokens actually loaded rather than full video length.
Older release← Sep 1, 16:03 UTCNewer release→ Sep 1, 20:03 UTC
All Gemini Docs releases →