Moondream 3 Preview
moondream3
Moondream 3 Preview is the original 9B mixture-of-experts vision-language checkpoint with 2B active parameters, for visual question answering, captioning, OCR, and visual reasoning. It accepts text or one image with optional reasoning, a 32,000-token context, and up to 4,096 output tokens.
Specification
most-agreed values
Context
32K
Max output
4K
Released
2026-10-16
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.30
Output
$2.50
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kilo · moondream | $0.30 | $2.50 | — | — | 32K | 4K | — |
| nano-gpt · moondream | $0.30 | $2.50 | — | — | 32K | 4K | — |
| openrouter · moondream | $0.30 | $2.50 | — | — | 32K | 4K | — |
