TL;DR
- Wan 2.6 Flash image-to-video (
wan2.6-flash/image-to-video) bills per second, set by resolution and audio: silent 720p at $0.029/s ($0.145 for 5 s), audio 720p $0.0575/s, silent 1080P $0.043/s, audio 1080P $0.086/s. - Durations are 5 / 10 / 15 s only; the output aspect follows the input image (portrait in, portrait out).
- Live on HiAPI: upload one image on the model page. New accounts get 200 free credits. API usage is in the guide.
Price table: four combinations
| Tier | Per second | 5 s | 10 s | 15 s | $10 yields (5 s) |
|---|---|---|---|---|---|
| 720p silent (default) | $0.029 | $0.145 | $0.29 | $0.435 | 68 |
| 720P · Sound On | $0.0575 | $0.2875 | $0.575 | $0.8625 | 34 |
| 1080P · Sound Off | $0.043 | $0.215 | $0.43 | $0.645 | 46 |
| 1080P · Sound On | $0.086 | $0.43 | $0.86 | $1.29 | 23 |
HiAPI current prices, checked October 21, 2026. Relative to the default: audio doubles, 1080P is ~1.5×, both together ~3×. Failed tasks refund.
Real clips at all four combinations
There's no same-prompt-across-tiers set in the archive; the first three share one fox input image with different prompts, stated as-is:
| Tier | Clip | Notes |
|---|---|---|
| 720p silent $0.145 | Fox → | 1280×720 · 5 s · defaults |
| 720p audio $0.2875 | Morning fox → | 1280×720 · 5 s · audio: true, same fox input, different prompt |
| 1080P silent $0.215 | Desert convertible → | 1918×1080 · 5 s · different input |
| 1080P audio $0.43 | Fox 1080P → | 1918×1080 · 5 s · fox input, yet another prompt |
All real wan2.6-flash/image-to-video clips; same-input combinations are flagged, and prompt differences are stated — compare tiers, not compositions.
What you can see:
- Silent versus audio shows in the track: with
audioon, ambience arrives with the picture (the morning fox carries forest sound). - 720p versus 1080P shows in sharpness: fur and dust read crisper in the two 1080P clips.
Spending less
- The default tier is cheapest: silent 720p at $0.145 for 5 s — iterate composition and prompts here.
- Audio on demand: pass
audio: trueonly when you want ambience (it doubles the rate); score in post otherwise. - 1080P for finals only: draft at 720p and upgrade — silent 1080P is still just $0.215.
- Aspect is free: upload a portrait for vertical output; ratios never cost extra.
Compared with related i2v models (HiAPI prices, 720p per second)
| Model | Silent | Audio | Notes |
|---|---|---|---|
wan2.6-flash/image-to-video (this model) | $0.029 | $0.0575 | 5/10/15 s; aspect follows image |
wan2.7-video/image-to-video | $0.1 | — | media input; 1080P $0.167 |
ltx-2.5-fast/image-to-video | $0.043 | same | Free audio; 12 durations; 1080P $0.086 |
grok-imagine-1.5-lite/image-to-video | $0.043 (sound built in) | same | +$0.015 input-image fee per clip |
grok-imagine-1.5/image-to-video | $0.0214 | same | 480p $0.0114 |
Silent 720p on Wan 2.6 is the entry price of this group;,.
Monthly budgets (5 s per clip)
| Clips / month | 720p silent | 720p audio | 1080P silent | 1080P audio |
|---|---|---|---|---|
| 100 | $14.50 | $28.75 | $21.50 | $43.00 |
| 500 | $72.50 | $143.75 | $107.50 | $215.00 |
| 1,000 | $145.00 | $287.50 | $215.00 | $430.00 |
Silent-heavy pipelines save the most: 800 silent 720p drafts plus 100 silent 1080P finals runs about $137.00 a month.
FAQ
Can I set any duration?
No — only 5, 10, or 15 seconds; other values return a 400.
Does the aspect follow the input?
Yes. No aspect parameter — portrait in gives portrait out, 3:4 gives 3:4.
How do I enable audio?
Pass audio: true explicitly; it bills at the Sound On rate.
How many clips does $10 buy?
About 68 at the default tier (720p silent, 5 s).
Do failures cost anything?
No. Validation rejections never bill.
Next: take one image and run a default-tier clip ($0.145 for 5 s); four scene templates are in the prompt guide, and whether to upgrade to Wan 2.7 is answered in the .
