Foundation video model

Vidu Q3 Turbo

Vidu Q3 Turbo supports text-to-video, image-to-video, start/end-frame and reference-to-video workflows with synchronized generated audio, including all-audio, speech-only and sound-effects-only modes. Compared with Q2 Turbo, Q3 Turbo adds text-to-video and reference-to-video and extends main-route clips up to 16 seconds. Vidu's official live price table currently lists 12 credits per 720p generated second, while its documentation pricing page still lists 11 credits ($0.055); both values are shown with their source and the conflict remains unresolved. Provider prices and matched-prompt completion times vary materially by route. Vidu Q3 Turbo is distinct from the separately tracked Q3 Drama model.

Official site View pricing Updated Sep 23, 2026
Key facts

Verified model snapshot

Maximum duration1–16s for T2V/I2V/start-end; 3–16s for reference-to-videoVerified Sep 23, 2026
Maximum resolution1080p canonical; provider-only 360p is not a Vidu model tierVerified Sep 23, 2026
Native audioYesVerified Sep 23, 2026
API statusavailableVerified Sep 23, 2026
Version delta

What changed

Pricing & providers

Where to access this model

Provider

Vidu Official API

12 observed offers

Last checked Sep 23, 2026

View 12 offer details
/ent/v2/* · text image start end · 540p

Vidu credits 7 / credits per generated second

7 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Current live table; 720p conflicts with docs/pricing 11 credits/$0.055s.

Source ↗
/ent/v2/* · text image start end · 540p

Vidu credits 4 / credits per generated second

4 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Off-peak task may complete within 48h.

Source ↗
/ent/v2/* · text image start end · 720p

Vidu credits 12 / credits per generated second

12 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Current live table; 720p conflicts with docs/pricing 11 credits/$0.055s.

Source ↗
/ent/v2/* · text image start end · 720p

Vidu credits 6 / credits per generated second

6 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Off-peak task may complete within 48h.

Source ↗
/ent/v2/* · text image start end · 1080p

Vidu credits 13 / credits per generated second

13 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Current live table; 720p conflicts with docs/pricing 11 credits/$0.055s.

Source ↗
/ent/v2/* · text image start end · 1080p

Vidu credits 7 / credits per generated second

7 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Off-peak task may complete within 48h.

Source ↗
/ent/v2/reference2video · reference to video · 540p

Vidu credits 4 / credits per generated second

4 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Source ↗
/ent/v2/reference2video · reference to video · 540p

Vidu credits 2 / credits per generated second

2 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Source ↗
/ent/v2/reference2video · reference to video · 720p

Vidu credits 10 / credits per generated second

10 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Source ↗
/ent/v2/reference2video · reference to video · 720p

Vidu credits 5 / credits per generated second

5 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Source ↗
/ent/v2/reference2video · reference to video · 1080p

Vidu credits 13 / credits per generated second

13 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit

Source ↗
/ent/v2/reference2video · reference to video · 1080p

Vidu credits 7 / credits per generated second

7 Vidu credits / credits_per_generated_second · 0.005 USD per Vidu_credit; Off-peak route

Source ↗
Provider

Replicate

3 observed offers · from $0.04/generated second

Last checked Sep 23, 2026

View 3 offer details
Replicate Predictions API · text image start end · 540p

USD 0.04 / generated second

0.04 USD / per_generated_second

Source ↗
Replicate Predictions API · text image start end · 720p

USD 0.06 / generated second

0.06 USD / per_generated_second

Source ↗
Replicate Predictions API · text image start end · 1080p

USD 0.08 / generated second

0.08 USD / per_generated_second

Source ↗
Provider

Runware

3 observed offers · from $0.026/generated second

Last checked Sep 23, 2026

View 3 offer details
Runware videoInference · text or image to video · 360p

USD 0.026 / generated second

0.026 USD / per_generated_second

360p is provider-specific; not canonical Vidu resolution.

Source ↗
Runware videoInference · text or image to video · 720p

USD 0.0357 / generated second

0.0357 USD / per_generated_second

Source ↗
Runware videoInference · text or image to video · 1080p

USD 0.0423 / generated second

0.0423 USD / per_generated_second

Source ↗
Provider

fal

2 observed offers · from $0.035/generated second

Last checked Sep 23, 2026

View 2 offer details
fal-ai/vidu/q3/text-to-video/turbo · text to video · 360p / 540p

USD 0.035 / generated second

0.035 USD / per_generated_second

Source ↗
fal-ai/vidu/q3/text-to-video/turbo · text to video · 720p / 1080p

USD 0.035 / base rate with multiplier

0.035 USD / base_rate_with_multiplier · $0.035 per video second × 2.2 for 720p/1080p

Preserve formula; Codex may normalize.

Source ↗
Provider

MachGen

6 observed offers · from $0.015/generated second

Last checked Sep 23, 2026

View 6 offer details
MachGen unified API · managed t2v i2v r2v · 540p

USD 0.015 / generated second

0.015 USD / per_generated_second

Source ↗
MachGen unified API · managed t2v i2v r2v · 540p

USD 0.018 / generated second

0.018 USD / per_generated_second

Source ↗
MachGen unified API · managed t2v i2v r2v · 540p

USD 0.02 / generated second

0.02 USD / per_generated_second

Source ↗
MachGen unified API · managed t2v i2v r2v · 720p

USD 0.03 / generated second

0.03 USD / per_generated_second

Source ↗
MachGen unified API · managed t2v i2v r2v · 720p

USD 0.04 / generated second

0.04 USD / per_generated_second

Source ↗
MachGen unified API · managed t2v i2v r2v · 720p

USD 0.045 / generated second

0.045 USD / per_generated_second

Source ↗
Provider

Roko API

12 observed offers · from $0.019624/generated second

Last checked Sep 23, 2026

View 12 offer details
/v1/videos/tasks · text to video · 540p

USD 0.034342 / generated second

0.034342 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · image to video · 540p

USD 0.034342 / generated second

0.034342 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · start end · 540p

USD 0.034342 / generated second

0.034342 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · reference to video · 540p

USD 0.019624 / generated second

0.019624 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · text to video · 720p

USD 0.0589 / generated second

0.0589 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · image to video · 720p

USD 0.0589 / generated second

0.0589 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · start end · 720p

USD 0.0589 / generated second

0.0589 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · reference to video · 720p

USD 0.0491 / generated second

0.0491 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · text to video · 1080p

USD 0.063778 / generated second

0.063778 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · image to video · 1080p

USD 0.063778 / generated second

0.063778 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · start end · 1080p

USD 0.063778 / generated second

0.063778 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
/v1/videos/tasks · reference to video · 1080p

USD 0.063778 / generated second

0.063778 USD / per_generated_second

Fresh Sep-22 route; final invoice may reconcile to upstream credits × $0.004906.

Source ↗
View detailed pricing
Derived signals

What stands out

Evidence-backed signals

  • Native audio is positively verified from an entity-supporting source.
  • Maximum duration is recorded as 1–16s for T2V/I2V/start-end; 3–16s for reference-to-video.
  • Official API access is verified as available.
Public test evidence

Recorded test runs

Hands-on testing pending. No quality score or first-hand verdict is shown until a complete raw test record is attached.
External evidence

Independent reports and examples

These observations belong to the named publishers and providers; they are not FrameSignal hands-on tests.

Artificial Analysis · Artificial Analysis

end to end time

Same prompt/provider comparison; timing varies by run.

Reported metric: fal.ai: 45.6s; Replicate: 84.1s seconds

Reported result: Same prompt/provider comparison; timing varies by run.

Prompt: Sculptor hovering in a botanical garden; handheld sway; desaturated travelogue.

Settings: target: 720p 5s benchmark configuration · providers: ["fal.ai","Replicate"]

Open source ↗
Artificial Analysis · Artificial Analysis

end to end time

Same prompt/provider comparison; timing varies by run.

Reported metric: Replicate: 55.6s; fal.ai: 56.7s seconds

Reported result: Same prompt/provider comparison; timing varies by run.

Prompt: Border collie in autumn orchard; dappled light; orbiting crane shot.

Settings: target: 720p 5s benchmark configuration · providers: ["Replicate","fal.ai"]

Open source ↗
Artificial Analysis · Artificial Analysis

end to end time

Same prompt/provider comparison; timing varies by run.

Reported metric: fal.ai: 56.8s; Replicate: 187.9s seconds

Reported result: Same prompt/provider comparison; timing varies by run.

Prompt: Potter at a flickering night market; slow pan; anamorphic film.

Settings: target: 720p 5s benchmark configuration · providers: ["fal.ai","Replicate"]

Open source ↗
Artificial Analysis · Artificial Analysis

end to end time

Same prompt/provider comparison; timing varies by run.

Reported metric: fal.ai: 47s; Replicate: 50.2s seconds

Reported result: Same prompt/provider comparison; timing varies by run.

Prompt: Calligrapher on a sand dune; slow tilt; clay stop-motion.

Settings: target: 720p 5s benchmark configuration · providers: ["fal.ai","Replicate"]

Open source ↗
Artificial Analysis · Artificial Analysis

end to end time

Same prompt/provider comparison; timing varies by run.

Reported metric: fal.ai: 49.1s; Replicate: 68.9s seconds

Reported result: Same prompt/provider comparison; timing varies by run.

Prompt: Cyclist spiraling above a quiet river; overhead top-down; clay stop-motion.

Settings: target: 720p 5s benchmark configuration · providers: ["fal.ai","Replicate"]

Open source ↗
Runware · Runware

raw generation charge

Provider shows roughly 48–65s end-to-end for 6s 720p T2V examples.

Reported metric: 0.2145 USD

Reported result: Provider shows roughly 48–65s end-to-end for 6s 720p T2V examples.

Prompt: Aquaculture net-cleaning robot product demonstration; full prompt at source.

Settings: duration seconds: 6 · resolution: 720p · audio: true

Open source ↗
Runware · Runware

raw generation charge

Provider shows about 3m21s end-to-end for this example.

Reported metric: 0.17875 USD

Reported result: Provider shows about 3m21s end-to-end for this example.

Prompt: Logo reveal between supplied opening and closing frames; full prompt at source.

Settings: duration seconds: 5 · mode: first_last_frame

Open source ↗
External benchmarks

Benchmark snapshots

Text to Video Leaderboard · Sep 23, 2026

Q3 Turbo

text to videoElo1025 Elo · rank 28 · n=3,117
text to videorank28 rank · rank 28 · n=3,117
text to videosamples3117 comparisons · rank 28 · n=3,117
Open benchmark source ↗
Image to Video Leaderboard · Sep 23, 2026

Q3 Turbo

image to videoElo1030 Elo · rank 25 · n=3,267
image to videorank25 rank · rank 25 · n=3,267
image to videosamples3267 comparisons · rank 25 · n=3,267
Open benchmark source ↗
Model Detail Quality Analysis · Sep 23, 2026

Q3 Turbo

aggregate or model detailquality elo1105.98 Elo
Open benchmark source ↗
Capabilities

Capability matrix

Text to videoYes
Image to videoYes
Native audioYes
Reference imagesYes
Aspect ratios16:9, 9:16, 3:4, 4:3, 1:1
Compare with

Related public models

Alternatives

Related models to evaluate

Developer access

API

StatusavailableVerified Sep 23, 2026
PricingVidu credits convert at $0.005 per credit. The live Vidu table shows 720p general generation at 12 credits/$0.06 per second; the separate docs/pricing page still shows 11 credits/$0.055 per second. This official-source discrepancy is unresolved. Off-peak pricing is lower and may take up to 48 hours. Provider rates differ by route and billing basis.Verified Sep 23, 2026
Official accessDocumentation ↗
Open API record
Latest updates

Q3 Turbo change feed

View all updates
Evidence

Sources and verification