Glimpse
Elorian released Glimpse, its first model, as a research preview with API access. It reasons by cropping images and pulling video frames mid-reasoning.
Most multimodal models look at an image once, turn it into tokens and reason in text. Glimpse can go back to the source mid-reasoning, cropping into a region, pulling specific video frames or running code to measure and compare, which Elorian calls a visual scratch space. Elorian says a small team trained it on a few hundred GPUs and that it is much smaller than the frontier systems it is compared with.
- Date
- Friday 16 October 2026
- Lab
- Elorian
- Kind
- model
- Access
- research preview
- Price
- $0.60 per million tokens in, $3 per million tokens out
Figures
| Measure | Value | Measured by |
|---|---|---|
| API input price | $0.60 per million tokens | company |
| API output price | $3 per million tokens | company |
Elorian says Glimpse beats GPT-6 Astra on scientific chart reasoning and short-form video captioning. These are company evaluations and no scores were published in the article. The chat interface is waitlist-only.
Sources
This record was checked against its sources on 16 October 2026. How we check