how much does VACE cost?

$0.40/video. you pay per run from your inference shell credits. no subscription is required.

how do I run VACE via api?

call pruna/vace with the javascript or python sdk, the rest api, or `belt app run pruna/vace` from a terminal. the api reference on this page lists every input.

VACE is made by pruna and runs on inference shell. every pruna app is listed at https://inference.sh/apps/pruna.

can my agent use VACE?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

what are the alternatives to VACE?

other video apps on inference shell include P-Video-Animate, P-Video-Upscale, P-Video-2-Pro-Avatar, P-Video-2-Pro-Reference. they run through the same api, so switching is a one-line change.

VACE

VACE-14B video generation and editing from a prompt, with optional source video, mask and up to 3 reference images for consistent characters.

text to video video to video

run in browser →run via API

run with your agent

# install belt

$curl -fsSL https://cli.inference.sh | sh

# sign in (or set INFERENCE_API_KEY on a headless machine)

$belt login

# view schema & details

$belt app get pruna/vace

# run

$belt app run pruna/vace --input '{"prompt":"prompt"}'

maker: pruna
category: video
input → output: text → video, video → video
price: $0.40/video
runs via: api, javascript and python sdk, belt cli, mcp
updated: 2026-10-23

api reference

about

vace-14b video generation and editing from a prompt, with optional source video, mask and up to 3 reference images for consistent characters.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash

1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash

1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python

1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567result = client.run({8        "app": "pruna/vace",9        "input": {10            "prompt": "prompt"11        }12    })1314print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python

1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567# stream=True yields updates as they arrive8for update in client.run({9        "app": "pruna/vace",10        "input": {11            "prompt": "prompt"12        }13    }, stream=True):14    if update.get("progress"):15        print(f"progress: {update['progress']}%")16    if update.get("output"):17        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python

1# local file paths are automatically uploaded2result = client.run({3    "app": "pruna/vace",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python

1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python

1result = client.run({2    "app": "pruna/vace",3    "input": {4        "prompt": "prompt"5    },6    "webhook": "https://your-server.com/webhook"7}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}

eventstringtask.completed, task.failed or task.cancelled

timestampstringiso timestamp of the delivery

data.idstringtask id

data.short_idstringshort task id

data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)

data.status_textstringthe status as a word: completed, failed or cancelled

data.outputobjecttask output (when completed)

data.errorstringerror message (when failed, omitted otherwise)

data.session_idstringsession id (when the task ran in a session, omitted otherwise)

data.created_atstringiso timestamp

data.updated_atstringiso timestamp

5. schema

input

promptstring*

description of the video. be specific about characters, action, setting and camera.

src_videostring(file)

source video to edit or transform.

src_maskstring(file)

mask video or image marking the area of the source to edit.

src_ref_imagesarray

reference images for consistent characters (1-3 work best).

sizestring

output resolution (width*height).

default: "832*480"

options:"832*480""480*832""1280*720""720*1280"

frame_numinteger

number of frames to generate (up to 81).

default: 81min:1max:81

speed_modestring

speed versus consistency.

default: "Lightly Juiced 🍊 (more consistent)"

options:"Lightly Juiced 🍊 (more consistent)""Juiced 🔥 (more speed)""Extra Juiced 🚀 (even more speed)"

sample_stepsinteger

sampling steps. higher is better and slower.

default: 50min:1max:100

sample_solverstring

sampling algorithm.

default: "unipc"

options:"unipc""dpm++"

sample_guide_scalenumber

how closely to follow the prompt.

default: 5min:0max:20

sample_shiftinteger

sample shift.

default: 16min:0max:50

seedinteger

random seed for reproducible generation.

output

seedinteger

seed used for generation.

videostring(file)*

generated video.

more from pruna

P-Video-Animate

pruna/p-video-animate

$0.03/sec 720p, $0.06/sec 1080p

P-Video-Upscale

pruna/p-video-upscale

Std: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x

P-Video-2-Pro-Avatar

pruna/p-video-2-pro-avatar

$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k

P-Video-2-Pro-Reference

pruna/p-video-2-pro-reference

Output: cost $0.015-$0.105/sec, speed $0.02-$0.115/sec. Ref video: $0.03-$0.06/sec. Ref img: $0.005/img. Ref audio: $0.0015-$0.0025/sec

new models

ready to run VACE?

try in browser browse all apps

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.

products

capabilities

get started

learn

build

community

from the blog

VACE

api reference

about

1. calling the api

install the client

setup your api key

run and get result

stream live updates

2. authentication

3. files

automatic upload

manual upload

4. webhooks

5. schema

input

output

other video apps

more from pruna

new models

ready to run VACE?