The AI Loadout
←Back to models
Checked Active: 2026-10-17
Elorian

Elorian Glimpse

Reasoning over images and video: counting objects, following events across frames, reading charts, and labeling robot or job-site footage.

Evaluation Analysis: Released Oct 16, 2026. Elorian's first model, post-trained on an open-weights base. Text, image and video in, text out, with tool calling and structured outputs. Elorian's own table puts it ahead of GPT-6 Astra on chart reasoning (CharXiv-R 92.9), open-vocabulary counting and short video captions, and behind it on others such as Video-MME v2 and TOMATO. Available through Elorian's API and chat app, and on OpenRouter as elorian/glimpse (cached input $0.06).
Context Window262K tokens
Input Price / 1M$0.60
Output Price / 1M$3.00
Release Date2026-10-16

Specs and prices checked 2026-10-17 against the official page.

Used in these setups

Related skills and personas

Agent skills and bot personas that pair well with Elorian Glimpse.

Browse full directories:All Skills (>35)·All Personas (>15)

Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.