← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Moondream 3 Preview Pricing
Moondream · moondream-moondream3-preview
Input / 1M tokens
$0.300
Output / 1M tokens
$2.50
Context window
32k tokens
≈ 43 pages of text
Max output
4,096 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0014
1,000 requests / month$1.36/mo10,000 requests / month$13.60/mo100,000 requests / month$136.00/moEstimate your own workloadOpens the calculator with Moondream 3 Preview preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Handles basic visual question answering and image description tasks at low per-token cost with 32k context support.
The business tradeoff
Preview release and open-weights distribution introduce hosting variance and limited ecosystem tooling; reasoning depth remains constrained relative to larger closed models.
Head-to-head
Vendor list rates, as of Oct 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.