SFAI / MODEL PROFILE
Moondream3 Preview [Point]
Moondream 3 is a vision language model that brings frontier-level visual reasoning with native object detection, pointing, and OCR capabilities to real-world applications requiring fast, inexpensive inference at scale.
- Developer
- Unattributed (via fal)
- Input modalities
- image, text
- Output modalities
- text
- Context tokens
- Not reported
- Latest price observation
- 2026-09-27
- Lowest paired standard token quote
- Not available
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| fal.aifal | Not token-priced | $1.00 | unitspriced · USD | fal2026-09-27 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.