Moondream
Moondream: Moondream 3 Preview
moondream/moondream3-preview
Moondream 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 a 32K-token context and an optional reasoning mode.
Input
$0.3
/ 1M tokens
Output
$2.5
/ 1M tokens
Context window
32K
tokens
Limits
Context
32,000
tokens
Max output
4,096
13% of the context window
Parameters
9,268,626,928
Model facts
Author
Moondream
Tokenizer
Other
Modality
Text + Image -> Text
License
Other
Created
Oct 15, 2026
Hugging Face
moondream/moondream3-preview
Default generation parameters
temperature
0.2
top_p
0.9
Publication status
Hugging Face: verifiedLicense: publishedParameter count: published
Modalities
Input · TextInput · ImageOutput · Text
Generation controls
Include reasoningMax completion tokensMax tokensReasoningTemperatureTop p