Gemini adds agentic video understanding, cutting token usage by 88%
osanseviero · x · 2026-09-02
Gemini now supports agentic video understanding: instead of spending 200k tokens processing a long video, it uses tools to process video intelligently based on the prompt (analyzing transcription, adapting FPS, etc.). This leads to 88% fewer tokens, lower latency, and higher accuracy. A developer guide is available.
More from Models
- Fable 5.1 improves cybersecurity capabilities with significant reduction in fallbacks — ClaudeDevs · 2026-09-02
- Fable 5.1 release: Doubles scientific agent scores, cuts costs by 25% — mark_k · 2026-09-02
- Anthropic quietly launches Claude Fable 5.1 for "hardest challenges" — External-Grape-2978 · 2026-09-02
- Anthropic releases System Cards for Fable 5.1 and Mythos 5.1 — scaling01 · 2026-09-02
- Benchmarks for Claude Fable 5.1 and Claude Mythos 5.1 leaked — minxio_ · 2026-09-02
- Claude Fable 5.1 Scores Leak: 77.9% on OSWorld, Beating GPT-5.6 Sol Across Benchmarks — Scobleizer · 2026-09-02