KovAPIKovAPI
AnnouncementsAll updates →
NoticeNezhaGate is now KovAPI — new address kovapi.com NoticeCompensation for recent video generation failures NewSeedance 2.0 Mini is back and 2.0 Fast adds 480P, at a launch price
简体中文English ✓Español한국어日本語Русский
Log in Get API Key
Video ● Operational Service status →

Veo 3.1

⧉
veo-3.1

Veo 3.1 is Google's AI video model. One endpoint, parameters pick the type: text-to-video with no reference; one image as the first frame, two as first and last frame; with image_role=reference, one to three images as subject or style references. The Fast tier is open: 720p or 1080p, landscape 16:9 or portrait 9:16, 8 seconds per clip with native audio. Asynchronous: submit, then poll the job id for a re-hosted video link (kept for 15 days). Billed per clip (720p $0.20, 1080p $0.22); failed jobs are refunded in full.

Text-to-videoImage-to-videoFirst/last frameAsync jobs
Get API Key → API Docs

Live Test · Playground

Try out Veo 3.1 right here (available after login).

Input

Video
Reference images0 / 3
Click to upload or drag files here jpg / png / webp / gif, up to 16 MB each or paste links
With multiple references, address them in the prompt as @Image1 / @Image2, e.g. "the character from @Image1 stands in the scene from @Image2". Without tokens the model decides on its own.
The Fast tier is open: 720p / 1080p, 8 seconds per clip, billed per clip and fully refunded on failure.

Output

video
Results will appear here after running.
🕑 Generated images and videos are kept for 15 days before 2026-10-29 09:49:40 UTC; from that time, they are kept for 7 days and existing files older than 7 days are removed.

About Veo 3.1

Veo 3.1 is Google's AI video model. On KovAPI one model and one set of parameters produce different kinds of video: no reference image is text-to-video; one image becomes the first frame for image-to-video, two become the first and last frame with the motion in between generated for you; and with image_role=reference, one to three images act as subject or style references. The Fast tier is open at 720p or 1080p, landscape 16:9 or portrait 9:16, 8 seconds per clip with native audio. Asynchronous: submit, then poll the job id for a re-hosted mp4 link (kept for 15 days). Billed per clip, failed jobs refunded in full.

Use cases

Text-to-video shorts

Generate an 8-second clip straight from a one-line prompt for concept tests, previs and bulk assets.

Bring a product shot to life

Use one image as the first frame and describe the camera move; product shots, posters and illustrations start moving naturally.

First-to-last-frame transitions

Give a first and a last frame and the model fills in the motion between them, ideal for openers, transformations and scene changes.

Consistent characters and style

Lock a character's look or the visual style with one to three references and generate a series of different shots.

How to choose

Text only? Use text-to-video. Already have the right frame? Send it as the first frame. Need exact opening and closing images? Use first + last frame (720p only). Keeping one character or style across several shots? Pass one to three images with image_role=reference. 1080p costs $0.02 more per clip than 720p; prefer it for final delivery.

FAQ

How does one model make different kinds of video?
The images you send and image_role decide it: no image is text-to-video; one is the first frame; two are the first and last frame; with image_role=reference, one to three are references. tier, resolution and size set the quality tier, resolution and orientation.
Which tiers and resolutions can I use now?
The Fast tier is open at 720p ($0.20 per clip) or 1080p ($0.22 per clip), always 8 seconds. Lite and Quality are not available right now; asking for them returns an error instead of silently switching tiers.
First frame, first + last frame or references?
First frame: the clip opens on your image. First + last frame: the clip opens on one image and ends on the other, with the motion generated in between (720p only). References: the people or style in the images appear in the video, but no image is used as a frame.
How is it billed? Am I charged for failures?
Per clip; the hold equals the final charge. A failed render, a content-policy block or a timeout is refunded in full, so you never pay for a video you did not get.

Related Models

Explore other models you can integrate.

View all →
Gemini Omni Flash Video

Gemini Omni Flash

gemini-omni-flash

Google's next-generation video model · 6 / 8 / 10 s

$0.050/s View →
Seedance 2.5 Video

Seedance 2.5

seedance-2.5

Text / image to video · up to 30 seconds

$0.158/s View →
Wan 3.0 Video

Wan 3.0

wan3.0-video

One endpoint, five modes · up to 30 seconds

$0.065/s View →
Seedance 2.0 Video

Seedance 2.0

seedance-2.0

Text / image to video · 5-15 seconds

$0.150/s View →
Seedance 2.0 Fast Video

Seedance 2.0 Fast

seedance-2.0-fast

Low latency · quick turnaround

$0.075/s View →
Grok Imagine Video 1.5 Video

Grok Imagine Video 1.5

grok-imagine-video-1.5

Billed per clip · up to 15 seconds

$0.300/clip+ View →