How to Use Moondream 3 Preview in Claude
Moondream 3 Preview answers questions about images, writes captions, and extracts visual details into JSON. It supports reasoning for harder visual questions, but tiny text can trip it up.
Prompts to try with Moondream 3 Preview in Claude
Copy an example into Claude, or ask in your own words.
Use Moondream 3 Preview to write one sentence of alt text for this image. Describe the main subject and action using only visible details.
Use Moondream 3 Preview to convert this pictured table into Markdown. Mark text you cannot read instead of filling it in.
Use Moondream 3 Preview to describe the products in this photo as JSON with one entry per product and keys for color, shape, and position.
Use Moondream 3 Preview with reasoning enabled to answer this question about the photo: which utensil is best suited to serving pasta? Explain using visible features.
Use Moondream 3 Preview to read the error message in this screenshot. Keep the answer brief and flag any tiny text that is unclear.
How to set up Moondream 3 Preview 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 Moondream 3 Preview
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": "moondream/moondream3-preview", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude finds Moondream 3 Preview on Spiral, shows the price and runs it.
Moondream 3 Preview providers and prices
Spiral runs Moondream 3 Preview through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.013327 per run at the default inputs. $0.39 per 1M input tokens, $3.25 per 1M output tokens.
Settings you can ask for
Ask Claude for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top p | 0 to 1 | ||
| Max tokens | 1 to 4096 | The most output tokens to generate. | |
| Temperature | 0 to 2 |
Every API field of Moondream: Moondream 3 Preview is on its tool page: open its card above.
What can you do with Moondream 3 Preview in Claude?
Get useful answers from photos and screenshots without describing every visible detail yourself. Ask a focused question or request a caption, a transcription, or a structured description.
Draft alt text
Turn website images into concise descriptions of the visible subject and action. Review the drafts in the context of the surrounding page.
Describe product photos
Extract visible product attributes such as color, shape, and arrangement for catalog descriptions. Ask it to mark details that cannot be determined from the photo.
Convert pictured tables into Markdown
Transcribe a clearly readable table from an image into editable Markdown. Check small print and ambiguous characters against the source.
Explain support screenshots
Describe the visible interface state or transcribe a readable error message to give a support agent concrete evidence.
Catalog an image collection
Create captions and structured descriptions that record the subjects, colors, and setting shown in each image.
Check image descriptions
Ask whether a photo supports a specific description, and request the visible evidence behind the answer.
Prepare visual observation reports
Summarize what is visible in a scene photo using a consistent set of requested details, such as object type, color, and position.
More on Moondream 3 Preview and Claude
Overview
Moondream 3 Preview in other agents
Questions about Moondream 3 Preview in Claude
Can Claude use Moondream 3 Preview?
Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Moondream 3 Preview like any built-in tool.
How much does Moondream 3 Preview cost in Claude?
Up to $0.013327 per run at the default inputs. $0.39 per 1M input tokens, $3.25 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 Moondream 3 Preview in Claude?
No. Spiral runs Moondream 3 Preview on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Moondream 3 Preview 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 Moondream 3 Preview runs?
Moondream 3 Preview runs in the background. Claude starts the run, checks on it and gives you the text, json when it's ready.
What is Moondream 3 good at?
Moondream 3 answers questions about images, describes scenes, and turns visible details into structured text. Useful tasks include product descriptions, alt text, and checking whether an image matches a description.
Can Moondream 3 read text in images?
Yes, including converting a pictured table into Markdown. Tiny fonts are a documented weakness, so check small text against the original image.
Can Moondream 3 return JSON?
Yes. Specify the keys you want and describe what each entry should represent, such as one object per visible product with its color and position.
How much context can Moondream 3 Preview handle?
The model card documents a usable context length of 32K tokens. That describes context capacity, not a promise of a 32K-token answer.
Does Moondream 3 use a fixed image resolution?
Moondream resizes images into overlapping tiles rather than using one fixed resolution. Its documentation describes roughly 378-by-378-pixel tiles, with up to 12 local tiles plus a global view.
Start using Moondream 3 Preview 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


