All models

Moondream 3.1

A small model for answering questions about images, describing them and reading text in them.

Last updated October 16, 2026.

Costs here use the prices AI companies charge software developers, so they show relative cost, not your monthly bill. See what ChatGPT, Claude and Gemini charge you.

Made by Moondream. Single-purpose.

What it costs

1,000-word essay: under 1 cent
100 chat messages: $0.41 (about 41 cents)
50-page PDF summary: $0.01 (about 1 cent)

Based on list prices and the assumptions on How we work. Your real cost will differ.

At a glance

Smartness: Not rated yet (our banding of the Artificial Analysis score, where available)
Reads at once: about 50 pages (rule of thumb)
Understands: text, pictures
Free to download and run yourself: Yes
Free to use: Not free for developers. Free app plans

Best for

describing imagesreading text in photos

Watch out for

Reads very little at once and gives short answers.

Appears in

Best AI for pictures, audio and video

Frequently asked

How much does Moondream 3.1 cost to use?
A 1,000-word essay costs about under 1 cent; summarizing a 50-page PDF about $0.01 (about 1 cent). These are developer (API) prices, not an app subscription.

What is Moondream 3.1 best for?
A small model for answering questions about images, describing them and reading text in them.

How much can Moondream 3.1 read at once?
About 50 pages (a rule of thumb: 32,000 tokens at roughly 500 words a page).

Can I download Moondream 3.1 for free?
Yes, the model files are published, though running a large one needs powerful hardware.

Under the hood

Maker	Moondream
Price per 1M input tokens	$0.30
Price per 1M output tokens	$2.50
Context size	32K tokens (32,000)
Artificial Analysis Intelligence Index	Not reported (source, via OpenRouter)
Open weights	Yes (Hugging Face: moondream/moondream3.1-9B-A2B)
Speed	Not measured yet
Listed	2026-10-15

Maker's description (technical)

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

View on OpenRouter. Our verdict above is editorial, not benchmarked by us.