Vidu Q3 turbo vs pro API price per second: 540p, 720p, 1080p
Vidu lists Q3-turbo from $0.035 and Q3-pro from $0.045 per second, half price off-peak. The per-second table, a 10-second cost, and what Sume offers instead.

On Vidu's API pricing page (read 2026-10-02), Q3-turbo costs from $0.035 per second at 540p to $0.065 per second at 1080p, and Q3-pro costs from $0.045 to $0.12 per second. Off-peak runs are listed at roughly half. A credit is $0.005, so every dollar figure below is credits times half a cent.
The per-second table
Both Q3 models take 1 to 16 seconds per clip. The page prints credits per second and the dollar equivalent for peak and off-peak.
| Model and resolution | Peak credits/s | Peak $/s | Off-peak credits/s | Off-peak $/s |
|---|---|---|---|---|
| Q3-pro 1080p | 24 | $0.12 | 12 | $0.06 |
| Q3-pro 720p | 20 | $0.10 | 10 | $0.05 |
| Q3-pro 540p | 9 | $0.045 | 5 | $0.025 |
| Q3-turbo 1080p | 13 | $0.065 | 7 | $0.035 |
| Q3-turbo 720p | 11 | $0.055 | 6 | $0.03 |
| Q3-turbo 540p | 7 | $0.035 | 4 | $0.02 |
What a 10-second clip costs
Multiplying the printed rates by 10 seconds: a Q3-pro 1080p clip is 240 credits, $1.20 at peak and $0.60 off-peak. A Q3-turbo 1080p clip is 130 credits, $0.65 at peak and $0.35 off-peak. The cheapest cell, Q3-turbo 540p off-peak, is $0.20 for 10 seconds.
The step from turbo to pro at 1080p is about 1.8 times the price at peak. Whether that is worth it is a quality decision you can only make by rendering your own prompts on both.
Older Vidu models on the same page
The page also lists Q2 and Q1. Q2 image-to-video is priced as a base plus a per-second increment (Q2-turbo at 720p is listed at 8 credits plus 10 credits per second, or $0.04 plus $0.05 per second), and Q1 is listed at 80 credits, $0.40, for a 5-second 1080p generation with half price off-peak. If you are budgeting a long-running integration, check which model your code actually calls, because the formula differs.
What Sume does differently
Sume's video catalog does not include a Vidu model. Its video docs list families such as seedance-2.5, wan-3.0, minimax-h3 and gemini-omni-flash-1.1, each with its own durations; most accept 4 seconds or more, so Vidu's 1-second floor has no equivalent there.
There is no off-peak discount either. A Sume job runs when you submit it, is reserved at provider list times 1.25, and usage.cost reports what was billed. If half-price scheduling matters for a batch, Vidu's page is where that option lives; if a USD wallet and one polling API matter more, price the catalog models from GET /v1/videos/models.
Sources
Related posts
More in Pricing
- WaveSpeed starting price: lowest resolution, and a 10 s clip cost
WaveSpeed's page says starting prices are list prices at the lowest resolution or quality. At those rates a 10-second clip runs $0.30 to $1.80. Table inside.
- WellSaid Starter 20 minutes vs Sume TTS per character: cost per hour
WellSaid sells narration as download minutes per plan. Sume bills per character. Cost per minute for each WellSaid plan against Sume at the same speaking rate.
- What is one AI credit worth in dollars? Runway, Vidu, Pika, Topaz
One credit is $0.01 on Runway's API, $0.005 on Vidu, about $0.011 on a Pika plan and $0.08 to $0.12 on Topaz. Convert to dollars before you compare.
- Why Sume usage rows add up to more than you spent
Summing rows from GET /v1/usage overstates spend: refunded rows keep their hold amount. Read summary.debited_usd for a thread, run or job instead.
Written by Sume