Google Veo 3.1

Things move and fall the most convincingly on this list, and people talk with real mouth movement. Made by Google. 4 to 8 seconds, 720p to 4k, with sound. From $0.11 a second.

veo-3.1

Get API key API reference Add funds

TypeVideo

InputsText, First frame, References

Length4 to 8 s

Resolution720p, 1080p, 4k

SoundOn by default

Aspect ratioauto, 16:9, 9:16

From$0.11 / s

UpdatedOct 28, 2026

Pricing

Setting	MiniAPI	fal	Difference
720p/1080p silent	$0.11 / s	$0.10	+10%
720p/1080p audio	$0.165 / s	$0.15	+10%
4K silent from references	$0.11 / s	$0.10	+10%
4K audio from references	$0.165 / s	$0.15	+10%
4K silent words only	$0.33 / s	$0.30	+10%
4K silent from a frame	$0.33 / s	$0.30	+10%
4K audio words only	$0.385 / s	$0.35	+10%
4K audio from a frame	$0.385 / s	$0.35	+10%

Example costs

Setting	4 s	6 s	8 s
720p/1080p silent	$0.44	$0.66	$0.88
720p/1080p audio	$0.66	$0.99	$1.32
4K silent from references	$0.44	$0.66	$0.88
4K audio from references	$0.66	$0.99	$1.32
4K silent words only	$1.32	$1.98	$2.64
4K silent from a frame	$1.32	$1.98	$2.64
4K audio words only	$1.54	$2.31	$3.08
4K audio from a frame	$1.54	$2.31	$3.08

Parameters

Name	Required	Values	Default	Description
negative_prompt	No	text		What to keep out of the result.
prompt	Yes	text		What to make, in plain words.
image_url	For first frame	https URL		A picture to start from. We fetch it and keep a copy for the job.Only with first frame
image_urls	For references	https URLs		Pictures to use as references.Only with references
aspect_ratio	No	auto, 16:9, 9:16	auto	Shape of the result, for example 16:9 or 9:16.
duration	No	4s, 6s, 8s	8s	Length in seconds. The price changes with it.
resolution	No	720p, 1080p, 4k	720p	Output size. Higher is sharper, slower and costs more.
generate_audio	No	true, false	true	Add sound effects, background sound and speech.
auto_fix	No	true, false	false	Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them.
safety_tolerance	No	1 to 6	4	How strict the model's own content filter is. Lower is stricter.
seed	No	integer		The same seed with the same settings gives a similar result. Leave it out for a random one.

Quickstart

curl -X POST "https://api.minicut.ai/v1/queue/veo-3.1" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox runs through snow at dawn","duration":"4s"}'

200 OK

{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/veo-3.1/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/veo-3.1/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/veo-3.1/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.660000",
  "currency": "USD"
}

Compare

Model	Maker	Max length	Resolution	Sound	From	vs fal
Google Veo 3.1	Google	8 s	720p, 1080p, 4K	Yes	$0.11 / s
Seedance 2.5	ByteDance	30 s	480p, 720p, 1080p	Yes	$0.16 / s	-27%
Seedance 2.0	ByteDance	15 s	480p, 720p, 1080p, 4K	Yes	$0.10 / s	-26%
Kling 3.0	Kling	15 s		Yes	$0.0924 / s
H3 Max	MiniMax	15 s	480P, 768P, 1080P	No	$0.055 / s