Models / moondream
Moondream 3 Preview
by moondream ·
moondream/moondream3-previewMoondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
reasoningvisionreleased 2026-10-15
Legal score · raw
-
not yet benchmarked
Context
32K
max output 4K
Input
$0.38
per 1M tokens
Output
$3.13
per 1M tokens
Suite cost
-
no run recorded
Capabilities
Modalities
in textimage
out text
Request parameters it accepts
include_reasoningmax_completion_tokensmax_tokensreasoningtemperaturetop_p
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.