Hub/Models/moondream/moondream3-preview
moondreamtext + image → text

Moondream: Moondream 3 Preview

Canonical ID: moondream/moondream3-preview

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.30
Input
Completion Output (1M Tokens)
$2.50
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
31.25k tokens
Context

Supported Parameters & Features

include_reasoningmax_completion_tokensmax_tokensreasoningtemperaturetop_p