How to Use Elorian Glimpse in Claude
Elorian Glimpse analyzes charts, counts objects, and follows actions across video frames. Its focus is visual reasoning, including spatial relationships and physical cause and effect.
Prompts to try with Elorian Glimpse in Claude
Copy an example into Claude, or ask in your own words.
Use Elorian Glimpse to explain this chart. Describe the axes, the main comparison, and the visible evidence for your conclusion in under 200 words.
Use Elorian Glimpse to count only the open pliers in this photo. Give the total, describe each counted object’s location, and list uncertain cases separately.
Use Elorian Glimpse to describe this short video in order. Include the main actions and their timestamps, and flag anything you cannot determine visually.
Use Elorian Glimpse to follow the animals through this clip and count each one once. Explain which visual features you used to distinguish them.
Use Elorian Glimpse to interpret the movement in this silent animation. Describe the postures and transitions that support your answer.
How to set up Elorian Glimpse in Claude
Pick the way that suits you. Each takes about two minutes.
Use the Claude connector
- Add Spiral to Claude
Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:
https://api.spiral.ai/mcp
- Keep the detected sign-in and click Add
Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.
- Click Connect
The connector page opens. Connect takes you to Spiral in your browser.
Use the Spiral skill
- Send Claude this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Elorian Glimpse
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "elorian/glimpse", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude finds Elorian Glimpse on Spiral, shows the price and runs it.
Elorian Glimpse providers and prices
Spiral runs Elorian Glimpse through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.016002 per run at the default inputs. $0.78 per 1M input tokens, $3.90 per 1M output tokens.
Settings you can ask for
Ask Claude for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Max tokens | 1 to 256000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Elorian: Glimpse is on its tool page: open its card above.
What can you do with Elorian Glimpse in Claude?
Get explanations of charts, crowded scenes, and actions in video. Ask follow-up questions about the visual evidence and have the chat app separate observations from interpretations.
Explain scientific charts
Ask Elorian Glimpse to explain a chart’s axes, trends, and comparisons. Request the visible evidence behind each conclusion.
Caption short videos
Use Elorian Glimpse to describe subjects and actions in order. Request a concise event list for reviewing or organizing clips.
Count objects in photos
Give Elorian Glimpse a crowded image and a precise counting rule, such as counting only open tools or one equipment category.
Track unique objects through motion
Ask Elorian Glimpse to follow objects through camera movement and report a unique count. Request separate notes for uncertain identities.
Label robot demonstrations
Use Elorian Glimpse to draft event labels for pick-and-place footage. Review the proposed event boundaries before adding them to training data.
Review spatial relationships
Ask Elorian Glimpse to explain where objects sit relative to each other and how their visible arrangement supports a proposed physical consequence.
Describe animated movement
Use Elorian Glimpse to interpret movement in a silent sketch or animation. Ask which postures and transitions support its description.
More on Elorian Glimpse and Claude
Overview
Elorian Glimpse in other agents
Questions about Elorian Glimpse in Claude
Can Claude use Elorian Glimpse?
Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Elorian Glimpse like any built-in tool.
How much does Elorian Glimpse cost in Claude?
Up to $0.016002 per run at the default inputs. $0.78 per 1M input tokens, $3.90 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude plan is separate.
Do I need an OpenRouter account to use Elorian Glimpse in Claude?
No. Spiral runs Elorian Glimpse on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Elorian Glimpse in Claude?
About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.
Does Claude wait while Elorian Glimpse runs?
Elorian Glimpse runs in the background. Claude starts the run, checks on it and gives you the text, json when it's ready.
What is Elorian Glimpse good at?
Its documented strengths include chart analysis, object counting, and short-form video captioning. It also reasons about spatial relationships and physical cause and effect.
Does Elorian Glimpse generate images or video?
Glimpse accepts text, images, and video and returns text. Use it to explain visual material, count objects, or describe actions.
How much context and output does Elorian Glimpse support?
OpenRouter documents a 262,144-token context window and up to 256,000 completion tokens. These are token limits, not video duration or pixel limits.
How should I ask Elorian Glimpse to count objects?
Define exactly what qualifies, including the object’s state, and specify whether you want visible objects or unique objects across a video. Ask for an itemized count and evidence for uncertain matches.
Can Elorian Glimpse control a robot directly?
Elorian demonstrates analysis of robot footage, including splitting pick-and-place activity into events. It describes direct robot control and calibrated reconstruction as work still ahead.
Start using Elorian Glimpse in Claude
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude:
set up https://spiral.ai/SKILL.md


