RELEASE · MODELS · #2129
Elorian releases Glimpse, a visual-reasoning model with a "visual scratch space"
Elorian, a Palo Alto startup that raised a $55M seed round, announced Glimpse as a research preview with API access and a waitlist for chat; the model repeatedly re-inspects images during reasoning using a mechanism it calls a "visual scratch space" (e.g., crop/zoom, frame selection, code measurements). Elorian says Glimpse was trained on a few hundred GPUs, is substantially smaller than frontier systems, is priced at $0.60 per million tokens in and $3 per million tokens out, and—according to the company—outperforms GPT-6 Astra on scientific chart reasoning and short-form video captioning on its benchmarks.
KEY POINTS
- Elorian, a Palo Alto startup that raised a $55M seed round, announced Glimpse as a research preview with API access and a waitlist for chat; the model repeatedly re-inspects images during reasoning using a mechanism it calls a "visual scratch space" (e.g., crop/zoom, frame selection, code measurements).
- Elorian says Glimpse was trained on a few hundred GPUs, is substantially smaller than frontier systems, is priced at $0.60 per million tokens in and $3 per million tokens out, and—according to the company—outperforms GPT-6 Astra on scientific chart reasoning and short-form video captioning on its benchmarks.
- If the approach reliably improves visual reasoning while being smaller and cheaper to run, it could accelerate applications that need precise scene understanding (robotics, labs, media) and shift model design toward iterative image inspection.
WHY IT MATTERS
If the approach reliably improves visual reasoning while being smaller and cheaper to run, it could accelerate applications that need precise scene understanding (robotics, labs, media) and shift model design toward iterative image inspection.