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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000003 | $0.300 |
| completion | 0.0000025 | $2.50 |
{
"temperature": 0.2,
"top_p": 0.9
}