Moondream 3 Preview
moondream/moondream3-preview
- context
- 32K
- modalities
- text, image → text
- capabilities
- Reasoning, Vision, Low cost
Overview
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...
Providers
- PrimeIntellectView PrimeIntellect
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| PrimeIntellect | $0.30 | $2.50 |
PrimeIntellect
- input / 1M
- $0.30
- output / 1M
- $2.50
Use this model
through Nautili
Route requests to Moondream 3 Preview through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.