Moondream3 Preview is Moondream's language model with a 32K context window and up to 4K output tokens, starting at $0.3 / 1M input and $2.50 / 1M output. A vision-language model from Moondream with 9B total and 2B active Mixture-of-Experts parameters, handling visual question answering, captioning, OCR, and visual reasoning.
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning✓
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.3 | $2.50 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Moondream3 Preview, ranked by cheapest on-demand price. The model needs about 22 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| g2-standard-4 |  GCP | nvidia-l4 | 24 GB | $0.705/hr | ||
| g6.xlarge |  AWS | L4 | 22 GB | $0.805/hr | ||
| g2-standard-8 | GCP | nvidia-l4 | 24 GB | $0.851/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Moondream3 Preview | 32K | $0.300 | $2.50 | Current | |
| Moondream3.1 9B A2B | 32K | $0.300 | $1.00 | Available |