Moondream 3 Preview
by Moondream · moondream/moondream3-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...
- Input / 1M tokens
- $0.30
- Output / 1M tokens
- $2.50
- Context
- 32K
Specs
| Input price | $0.30 / 1M tokens |
|---|---|
| Output price | $2.50 / 1M tokens |
| Context window | 32K tokens |
| Max output | 4.1K tokens |
| Reads | text, image |
| Writes | text |
| Tool calling | No |
| Reasoning | Yes |
| Listed | Oct 15, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
1 provider serves this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|
| PrimeIntellect | fp8 | 32K | 4.1K | $0.30 | $2.50 | 205 ms | 48 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- Moondream
Moondream 3.1
- Input
- $0.30
- Output
- $2.50
- Context
- 32K
- MiniMax
MiniMax M3
- Input
- $0.30
- Output
- $1.20
- Context
- 1.05M
- Cohere
Command A+
- Input
- $0.30
- Output
- $1.50
- Context
- 192K
- Meta
Muse Glimmer 30B
- Input
- $0.30
- Output
- $1.20
- Context
- 131K
- Google
Gemini 3.5 Flash Lite
- Input
- $0.30
- Output
- $2.50
- Context
- 1.05M
- Meituan
LongCat 2.0
- Input
- $0.30
- Output
- $1.20
- Context
- 1.05M