Providers and ModelsTencent

Hunyuan-Video-1.5

Hunyuan-Video-1.5

Provider: Tencent
Category: Video Generation
Endpoint: POST /v1/videos/generations
Context window: —
Served from: EmpirioLabs (Native Inference)

8.3B-parameter video model with native 720p output (upscalable to 1080p), strong motion coherence, and bilingual prompt understanding up to 10s.

At a glance

FieldValue
Model idhunyuan-video-1-5
Input modalitiestext
Output modalitiesvideo
Context window—
RegionEmpirioLabs (Native Inference)
Features1080p_upscale, bilingual
NewNo
Native inferenceYes

Pricing

ChargeSpecRate
480pper second (~2 min for 5s)$0.061
720pper second (~8 min for 5s)$0.29
1080p (upscaled)per second (~20 min for 5s)$0.67
Notes1080p limit5s max generations

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "hunyuan-video-1-5", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes—Scene description.
modeenumno"t2v"t2v: text-to-video. i2v: animate the attached image. · Allowed: t2v, i2v
resolutionenumno"720p"480p is the fastest tier. 1080p is upscaled and capped at 5s. · Allowed: 480p, 720p, 1080p
aspect_ratioenumno"16:9"Allowed: 16:9, 9:16, 1:1, 4:3, 3:4
durationnumberno5Clip length in seconds. 1080p is capped at 5s. · Range: 1 – 10
cfg_scalenumberno6Classifier-free guidance. Higher = follows prompt more strictly. · Range: 1 – 20
stepsnumberno30Diffusion steps. More = higher fidelity, slower. · Range: 10 – 50
imagestringno—Reference image URL for i2v mode.
negative_promptstringno""What to avoid.
seednumberno—Reproducibility seed.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/hunyuan-video-1-5.