Moondream: Moondream 3 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 …

moondream/moondream3-preview-20261013

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.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
32000
Published model ID
moondream3-preview
Capabilities
multimodal, reasoning, visionInput
Description source ↗

Published prices

1–2 / 2

Source specification observations

1–2 / 2

openRouter ↗

field
context_length
value
32000
normalized value
32000
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
4096
normalized value
4096
scope
source-model
source id
openRouter
confidence
1

Original sources

1–3 / 3

Hugging Face · moondream/moondream3-preview ↗

OpenRouter · Model page ↗

OpenRouter · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace