Glimpse
Glimpse is a multimodal visual reasoning model from Elorian, designed to understand and reason about images and video of the physical world. It accepts text, image, and video input, produces text, and supports tool calling.
Glimpse specs and pricing
- Provider: Elorian
- Released: October 17, 2026
- Context window: 262K tokens
- Max output: 256K tokens
- Input: text, images, video
- Output: text
- Price: $0.60 input / $3.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Glimpse is good at
- Reasoning about images
- Understanding video scenes
- Long-context visual analysis
To-dos to try with Glimpse
- Describe the objects and their spatial relationships in this image.
- Review this video and summarize what happens in each scene.
- Compare these two images and list the visible differences.
FAQ
- Who makes Glimpse? Glimpse is made by Elorian.
- Can Glimpse read images and video? Yes. Glimpse accepts images and video as input and is designed for visual understanding and reasoning.
- How much does Glimpse cost? Glimpse costs $0.60 per million input tokens and $3.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.1 credits ($1 = 100 credits).
- What is the context window of Glimpse? Glimpse can read up to 262K tokens at once and write up to 256K tokens in one reply.
- Can I use Glimpse without coding? Yes. In todo.is you pick Glimpse as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.