Pixverse v5.6

PixVerse · Video Generation

POST /v1/videos/generations

Generates videos from text or 1-2 frame image prompts up to 1080p, multiple aspect ratios, 5-10s durations, with optional synchronized audio.

At a glance

Field	Value
Model id	`pixverse-v5-6`
Input modalities	Text, Image
Output modalities	Video
Context window	-
Weight precision	-
Features	audio, styles
Native inference	No
New	No
Supported endpoints	`POST /v1/videos/generations`

Pricing

Charge	Spec	Rate
360p/540p 5s no audio	per video	$0.40
360p/540p 5s audio	per video	$0.80
360p/540p 8s no audio	per video	$0.80
360p/540p 8s audio	per video	$1.60
360p/540p 10s no audio	per video	$0.88
360p/540p 10s audio	per video	$1.76
720p 5s no audio	per video	$0.65
720p 5s audio	per video	$1.30
720p 8s no audio	per video	$1.30
720p 8s audio	per video	$2.60
720p 10s no audio	per video	$1.43
720p 10s audio	per video	$2.86
1080p 5s no audio	per video	$0.75
1080p 5s audio	per video	$1.50
1080p 8s no audio	per video	$1.50
1080p 8s audio	per video	$3.00

Example request

$ curl https://api.empiriolabs.ai/v1/videos/generations \
>   -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>   -H 'Content-Type: application/json' \
>   -d '{"model": "pixverse-v5-6", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	yes	-	Scene description.
`mode`	enum	no	`"t2v"`	t2v: text-to-video. i2v: animate the attached image. · Allowed: `t2v`, `i2v`
`resolution`	enum	no	`"1080p"`	Output resolution. Larger = higher fidelity but slower / more expensive. · Allowed: `360p`, `540p`, `720p`, `1080p`
`aspect_ratio`	enum	no	`"16:9"`	Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:2, etc.). · Allowed: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
`duration`	enum	no	`"5s"`	1080p only supports 5s and 8s. · Allowed: `5s`, `8s`, `10s`
`audio`	boolean	no	true	Generate native audio with the video.
`image`	string	no	-	Reference image URL. Required for i2v.
`image_end`	string	no	-	Optional last-frame image URL for image-to-video.
`style`	enum	no	`"none"`	Stylization preset. · Allowed: `none`, `anime`, `3d_animation`, `clay`, `comic`, `cyberpunk`
`thinking`	enum	no	`"auto"`	Whether the model uses chain-of-thought before generating. auto lets PixVerse decide. · Allowed: `auto`, `enabled`, `disabled`
`negative_prompt`	string	no	`""`	What to avoid (≤2048 chars).
`seed`	number	no	-	Reproducibility seed.

Notes

Generates videos from text or 1-2 frame image prompts up to 1080p with optional audio.

Uploaded media preprocessing

Image inputs smaller than 300px are upscaled, images larger than 4000px are downscaled, and oversized image uploads are recompressed before generation.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/pixverse-v5-6.