Runflow
Back to Gallery

google/veo3.1

Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on!

$0.4/second 2026-04-06

Install

pip install requests

Run the model

import requests

response = requests.post(
    "https://api.runflow.io/v1/run/veo3.1",
    headers={"Authorization": "Bearer RUNFLOW_API_KEY"},
    json={
    "prompt": "An astronaut in a white spacesuit with gold visor steps off a lander's bottom...",
    "duration": "8s",
    "resolution": "4k",
    "aspect_ratio": "16:9",
    "generate_audio": true
    },
)

data = response.json()
print(data["video"]["url"])

Input schema

ParameterTypeDescription
promptstringThe text prompt describing the video you want to generate
auto_fixbooleanWhether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.
durationstringThe duration of the generated video.
generate_audiobooleanWhether to generate audio for the video.
resolutionstringThe resolution of the generated video.
aspect_ratiostringAspect ratio of the generated video
safety_tolerancestringThe safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.
seedintegerThe seed for the random number generator.
negative_promptstringA negative prompt to guide the video generation.

Output schema

FieldTypeDescription
videostringThe generated video.

Related models

Start generating with Veo 3.1

Get API access in minutes. No GPU setup, no infrastructure to manage.