Optional WAV/MP3 voice URL per reference image/video: 1–10 seconds, at most 15 MB. Overrides the video voice, but does not dictate spoken words.Source for Voice references (opens in a new tab)
An explicit first frame overrides the ratio parameter.
Output billing
Output duration plus capped input-video usage: sum min(video duration, 5 / number of reference videos). Images and the first frame are excluded from this divisor; total billable input is at most 5 seconds.Source for Output billing (opens in a new tab)
Reference video billing
For two reference videos and one image, each video contributes at most 2.5 seconds. Images are free. The guide rounds 5/3 to 1.65 in examples without specifying general billing precision.Source for Reference video billing (opens in a new tab)
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Use an API key from the same region.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Video generation
720P input + output video1
$0.10
second
Video generation
1080P input + output video1
$0.15
second
Rate conditions
Output duration plus capped input-video usage: sum min(video duration, 5 / number of reference videos). Images and the first frame are excluded from this divisor; total billable input is at most 5 seconds.. International deployment; native published USD list tariff, not a currency conversion. No text-token or per-question estimate.
Task/result links expire after 24 hours. Full regional retention, training-use and enterprise contract terms are not verified by the API expiry statement.
Alibaba Model Studio · China (Beijing) · Chinese Mainland
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis; poll /api/v1/tasks/{task_id}. Use an API key from the same region.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Video generation
720P input + output video1
$0.082513
second
Video generation
1080P input + output video2
$0.137521
second
Rate conditions
Output duration plus capped input-video usage: sum min(video duration, 5 / number of reference videos). Images and the first frame are excluded from this divisor; total billable input is at most 5 seconds.. Chinese Mainland deployment; native published USD list tariff, not a currency conversion. Central pricing lists USD 0.086012/second, while this model card lists USD 0.082513/second. Confirm the account tariff before use. No text-token or per-question estimate.
Output duration plus capped input-video usage: sum min(video duration, 5 / number of reference videos). Images and the first frame are excluded from this divisor; total billable input is at most 5 seconds.. Chinese Mainland deployment; native published USD list tariff, not a currency conversion. Central pricing lists USD 0.143353/second, while this model card lists USD 0.137521/second. Confirm the account tariff before use. No text-token or per-question estimate.
Task/result links expire after 24 hours. Full regional retention, training-use and enterprise contract terms are not verified by the API expiry statement.
Caching
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Classification inference: this separately named native Wan 2.7/3.0 API release has no exact public checkpoint in the reviewed official Wan-AI inventory. Public Wan 2.1/2.2 models are excluded. API access and absence from that inventory do not independently prove undisclosed private checkpoint lineage; parameter counts and architecture are not transferred from public Wan models.
