Elorian releases Glimpse, its first AI model for visual reasoning

The company’s thesis is that current AI models, despite their language and code abilities, still cannot really see. Most multimodal models look at an image once, convert it into tokens and then reason in text, like describing a photo from memory. Glimpse returns to the source during reasoning. It can crop into a region, pull specific frames from a video, or run code to measure or compare what it is looking at, a mechanism Elorian calls a “visual scratch space.” The company compares it to someone pinching to zoom on a phone photo to double-check what they thought they saw.

Elorian CEO Andrew Dai, a former Google DeepMind researcher, said a board game night offered a clear example. He photographed a board game he had just finished playing with friends and asked a frontier model who was winning. The model could not answer. Board games “each have their own visual language, each have their own iconography, symbols,” Dai told TechCrunch. “To an adult, it’s quite easy to understand what’s going on with minimal text, but these models aren’t able to intuit what the symbols mean.” He added: “Humans can look at IKEA diagrams, with no text, and assemble IKEA furniture, right? Why can’t AI models?”

The approach is not completely new. OpenAI added crop-and-zoom during reasoning to its o-series models in 2025. Elorian’s pitch is that it built the whole model around the mechanism at low cost. The company said a small team trained Glimpse on a few hundred GPUs and that the model is substantially smaller than the frontier systems it has been benchmarked against.

Glimpse costs $0.60 per million input tokens and $3 per million output tokens, cheaper than mid-level models such as Sonnet and Sol but more expensive than lightweight models such as Haiku and Luna. According to Elorian’s evaluations, Glimpse outperforms even GPT-6 Astra on scientific chart reasoning and short-form video captioning, with competitive results on other visual reasoning tasks.

Elorian emerged from stealth six months ago with the seed round co-led by Striker Venture Partners, Menlo Ventures and Altimeter Capital, with participation from Nvidia and Google chief scientist Jeff Dean. Initial targets are companies with large amounts of video, including robotics firms, scientific labs, and media and creative companies. Longer term, Elorian wants to move from seeing to doing. That means building a model of a scene and using it to choose an action, including directly controlling robots. Dai said that next year the company aims to build “the world’s best visual reasoning model,” one that leads on every visual reasoning test.