Elorian: Glimpse
elorian/glimpse
Try Glimpse for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "elorian/glimpse"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "elorian/glimpse"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Glimpse is a visual reasoning model from Elorian, a Palo Alto startup, released as a research preview in October 2026. It accepts text, image, and video input and returns text. Elorian says it is post-trained on an open-weights base model.
During its reasoning, Glimpse can go back to the source material by cropping image regions, extracting video frames, or running code to compare visual data. Tool calling is supported, and the context window is 262,144 tokens.
Elorian reports these scores at maximum thinking effort, and they have not been independently verified: 92.90 on CharXiv-R (scientific chart reasoning), 95.36 on BabyVision, 93.60 on TOMATO (temporal reasoning), 83.75 on ERQA (embodied spatial reasoning), and 83.36 on FSC-147 (counting). Elorian also says it beats GPT-6 Astra on scientific chart reasoning and short-form video captioning.
It suits developers working on chart analysis, video understanding, counting, or robotics-related perception.
Context Window 262K
tokens
Max Output 256K
tokens
Input Cost $0.6
per million tokens
Output Cost $3
per million tokens
Input text, image, video
modalities
Tool Use Yes
Release Date Oct 16, 2026
Try Glimpse for free
Try Glimpse instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Glimpse by Elorian through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Glimpse is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Glimpse is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.6 |
| Output | $3 |
Glimpse was created by Elorian and released on Oct 16, 2026.
Glimpse supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Glimpse can generate up to 256K tokens in a single response.
Glimpse accepts the following input types: text, image, video. It produces: text.
Yes, Glimpse supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Glimpse API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Glimpse to your app for free
Developers can integrate Glimpse for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.