Pass IndexThe State of AISign in

Gemini Robotics ER 1.6 Preview

A vision-language model (VLM) that brings Gemini's agentic capabilities to robotics, understanding physical spaces and planning multi-step robotic tasks.

text + image + audio + video → text · made by Google

$0.5$2.5per Mtok in / out
Google

Sold by 2 ways

SellerLaneRate
Google 0 ways$0.5per Mtok in$2.5per Mtok out
Google apinot on the seller's list todaybatch$0.5per Mtok in$2.5per Mtok outai.google.dev · read 2026-08-24
Google 0 ways$1per Mtok in$5per Mtok out
Google apinot on the seller's list todaystandard$1per Mtok in$5per Mtok outai.google.dev · read 2026-08-24

Measured 1 standing

PlaceBoardMetricScore
24thof 24Blueprint bench 2 — Epoch AIScore0

About

Gemini Robotics ER 1.6 Preview — a text model from Google, placed 24th of 24 on Blueprint bench 2 — Epoch AI.

It takes text, images, audio and video and returns text, with a context window of 131,072 tokens. It was published in April 2026, trained on material up to January 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under agents. It stands 24th of 24 on Blueprint bench 2 — Epoch AI.

Every current figure

Maker
Google
Register
model
Takes
text + image + audio + video
Returns
text
Context
131,072 tokens
Longest answer
65,536 tokens
Published
April 2026
Knowledge to
January 2025
Licence
not read
Boards
1
Best place
24th of 24 — Blueprint bench 2 — Epoch AI

Known as 1 name

gemini-robotics-er-1.6-preview