Wan 2.5

Wan 2.5
Alibaba Cloud · Video Generation
POST /v1/videos/generations

Alibaba’s Wan 2.5 video model with text-to-video and image-to-video, native audio, optional custom audio tracks, and 480p to 1080p output.

At a glance

FieldValue
Model idwan-2-5
Model release date2025-09-24
Input modalitiesText, Image
Output modalitiesVideo
Context window-
Weight precision-
RegionSingapore
Featurestext_to_video, image_to_video, audio
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idsalibaba/wan-2.5, wan2.5

Pricing

ChargeSpecRate
480Pper second$0.05
720Pper second$0.10
1080Pper second$0.15

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
> -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
> -H 'Content-Type: application/json' \
> -d '{"model": "wan-2-5", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Scene description.
modeenumno"auto"Auto detects from attachments. t2v: text-to-video. i2v: animate one image. · Allowed: auto, t2v, i2v
resolutionenumno"1080p"Output resolution. · Allowed: 480p, 720p, 1080p
durationnumberno5Clip length in seconds. Only 5 or 10 are valid. · Range: 5 – 10
aspect_ratioenumno"16:9"Used for text-to-video; image-to-video follows the source image. 480p supports 16:9, 9:16, and 1:1 only. · Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
imagestringno-Source image URL for i2v.
audio_urlstringno-Optional custom audio track URL (WAV or MP3, about 3 to 30 seconds). Without it the model generates native audio.
negative_promptstringno""What to avoid.
seednumberno-Reproducibility seed.
prompt_extendbooleannotrueLet the service rewrite the prompt for better results.
watermarkbooleannofalseAdd a provenance watermark to the output.

Notes

Modes: text-to-video and image-to-video with native audio, or supply audio_url for a custom track (WAV or MP3, about 3 to 30 seconds). Durations are 5 or 10 seconds. 480p output supports 16:9, 9:16, and 1:1.


Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/wan-2-5.