The Orchestrator › Models › Moondream
Moondream: Moondream 3 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...
Specifications
| Provider | Moondream |
| Model ID | moondream/moondream3-preview |
| Context window | 32K tokens (32,000) |
| Modalities | text + image → text |
| Tokenizer | Other |
| Router sources | OpenRouter |
| Released | 2026-10-15 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | moondream/moondream3-preview | $0.3 | $2.50 | 32K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.3 | $2.50 | 32K |
Capabilities
Vision (image input)Controllable reasoning
Supported parameters
include_reasoning, max_completion_tokens, max_tokens, reasoning, temperature, top_p