someaistuff.
moondreamListed Oct 15, 2026

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 over images, with...

Compare
Context window32K
Max output4.1K
Provider endpoints2
Benchmark results0
Image inputReasoningOpen weights
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

2 quotes

OpenRouter

Catalog quote
Input
$0.30
Output
$2.50
USD / 1M tokens
32K context4.1K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDmoondream/moondream3-preview

PrimeIntellect

via OpenRouter

primeintellect/fp8 · quantization=fp8

Input
$0.30
Output
$2.50
USD / 1M tokens
32K context4.1K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoondream/moondream3-preview::primeintellect/fp8

Model specifications

Developer
moondream
Modality
Language
Context
32,000 tokens
Maximum output
4,096 tokens
Weights
Open weights
Provider listed
Oct 15, 2026
First discovered
Oct 16, 2026

Exact identities

  • openroutermoondream/moondream3-preview

Sources

OpenRouter ↗

Updated Oct 18, 2026

More from moondream

View all ↗
moondreamListed 2 days ago

Moondream: Moondream 3.1

Native object detection and pointing return structured coordinates; runs locally on Apple Silicon or NVIDIA GPUs.

32K context9BImage inputReasoningNo reported score
No reported score
$0.30in$2.50out/ 1M tokens · USDPrimeIntellect · via OpenRouter · 2 endpointsprimeintellect/fp8 · quantization=fp8
+Compare