← All models
Moondream · Multimodal
Moondream: Moondream 3.1
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...
ClosedIn: Text, ImageOut: Text
Input / M
$0.30 / M
Output / M
$2.50 / M
Cache read / M
—
Context
32K
Released
Oct 15, 2026