Source: vercel.com/changelog/elorian-ai-glimpse-now-available-on-ai-gateway
Glimpse follows objects through motion, interprets spatial relationships, and connects an action to its physical consequences, according to the announcement. The model can return to visual evidence while it works, such as zooming into a detail, revisiting a short interval of video, or tracking the same feature across frames.
The changelog lists scientific chart analysis, video captioning, visual counting and robotics data annotation as example use cases. Examples include checking whether a train is slowing down, keeping objects distinct through camera movement, and labeling completed actions in robot footage.
Developers can pass images or video as file parts through the AI SDK, using the model name elorian/glimpse, and set a reasoning level. AI Gateway can be configured in tools such as Claude Code, Codex and Cursor by running the Vercel CLI setup command.
Why it matters if you build agents
Agent builders who need to analyze images or video can add Glimpse through AI Gateway without a separate provider integration, using the same AI SDK calls as other models.
AI Gateway is described as having no markup on provider pricing and no platform fee on inference, including Bring Your Own Key requests, so costs follow the provider's rates.
Check the model's pricing and the video handling options in the changelog before relying on it for production video workloads.
Get stories like this every weekday
One short email with the day's agent tooling news.