# Gemini API adds agentic video understanding, up to 66% cheaper

Google · 2026-10-19 · Capability update

> Google's Gemini API gains agentic video understanding that uses tool calls to fetch only the media slices a prompt needs, making long-form video analysis more accurate and up to 66% cheaper.

This update bears on 2 kinds of work in 1 market. Highest level accepted: L2 Partial automation.

## The work it bears on

- [Implement tool use and agent workflows](https://surviagi.com/work/software-intelligent-systems-agent-workflows) (Model applications and agent systems): Claimed L3 · Accepted L2 · From the publisher only
- [Integrate models retrieval and context flows](https://surviagi.com/work/software-intelligent-systems-model-integration) (Model applications and agent systems): Claimed L3 · Accepted L2 · From the publisher only

## Published at

- [Source 1](https://x.com/googledevs/status/2112238816149058000)

---

Page: https://surviagi.com/updates/ev-72d7a3da1ecf202e05aa5ea16f2822742003c90e

Data generated 2026-10-20T00:16:30.842764+00:00; method activity-level-1; ontology 2.4.0.
Machine-proposed: no person has reviewed these readings, and the method is not calibrated.
Cite the page address together with the generation time.