All models

GoogleVideo

Veo 3.1

Google's premium Veo tier for coherent shots with native audio.

video/veo3.1
Try it in StudioUse with your agent or API

The mountain splits open with amber light and a colossal stone titan rises from it, snow and boulders cascading off its shoulders, its glowing amber eyes opening; the camera pushes slowly toward the knight's back and tilts up to follow the titan's head as it towers over her; her cape whips in the wind and she does not move. Epic scale, thunderous, slow. One continuous shot, no cuts, consistent character and world, correct anatomy and hands, no text, no letters, no logos, no captions.

Price
40 credits / second
Makes
Text to video, Image to video, Reference to video
Clip length
4 to 8 s

Best for

Veo 3.1 is Google's premium video model. Summer offers it for text to video, image to video, and subject-consistent video from up to three reference images, all with native audio.

  • Final trailer shots and store-page video where coherence matters most.
  • Intro and ending cinematics built around your own character art.
  • Keeping a hero character on-model across shots with reference images.

Put it together

Where Veo 3.1 fits in a game, with the models it works well with. Your agent runs every step.

Price

ModeModelPrice
Text to videoVeo 3.140 credits / second
Image to videoVeo 3.140 credits / second
Reference to videoVeo 3.1 Reference40 credits / second

Paid from your Summer credits.

Use it from code or your agent

Sign in once with summer login. Your agent or your code then runs it with your paid credits.

npx -y summer-engine@latest login
npx -y summer-engine@latest api run video/veo3.1 \
  --input '{"prompt":"a dragon circling a castle at dawn","duration":5}' \
  --download .

video/veo3.1: $0.40 per second of video. Paid from your Summer credits.

Inputs

What input takes for video/veo3.1. Send only what you need; Summer fills in tested defaults.

  • promptstringup to 4000 characters

    What happens in the clip. Needed without imageUrl.

  • imageUrlstringup to 2048 characters

    A public image URL to animate (image to video).

  • endImageUrlstringup to 2048 characters

    With imageUrl: the last frame. The same image as imageUrl makes a seamless loop. Models with an end frame: Seedance, Kling 3, Wan, Vidu, LTX 2.5, Luma, MiniMax.

  • referenceImageUrlsarray of string1 to 10 items

    Reference to video: public images of the characters, props or style to keep (with a reference model, e.g. kling-4-ref). Motion transfer: the character to move.

  • videoUrlstringup to 2048 characters

    An input clip (public URL, at most 20 s): restyle or reframe it, move a character with its motion, or add sound to it (e.g. kling-video-to-audio). Billed on the clip's length.

  • durationintegerDefault 5 · 1 to 20

    Seconds; the model renders its nearest supported length.

  • aspectRatioenumDefault 16:9
    • 16:9
    • 9:16
    • 1:1
    • 4:3
    • 3:4
    • 21:9
    • 3:2
    • 2:3
    • auto
  • negativePromptstringup to 1000 characters

    What the clip must not show.

  • resolutionenum

    Only a quality the model offers; leave out for its default.

    • 720p
    • 1080p
    • 4k
    • 480p
    • 768p
    • 2k
    • 768P
    • 1080P
    • 480P

Model docs · Summer API docs · Set up the Summer MCP server · Try it in the browser

Questions

What is Veo 3.1 good for in game development?
Veo 3.1 is Google's premium video model. Summer offers it for text to video, image to video, and subject-consistent video from up to three reference images, all with native audio. Typical game uses: final trailer shots and store-page video where coherence matters most; intro and ending cinematics built around your own character art; keeping a hero character on-model across shots with reference images.
How much does Veo 3.1 cost in Summer?
In Summer Studio: Veo 3.1 (text to video): 40 credits / second; Veo 3.1 (image to video): 40 credits / second; Veo 3.1 Reference (reference to video): 40 credits / second. It is charged from your Summer credits.
What can Veo 3.1 generate, and how long are the clips?
In Summer, Veo 3.1 supports text to video, image to video, and reference to video. Generated clips run 4, 6, and 8 seconds, in 16:9 and 9:16 aspect ratios at 720p, 1080p, and 4K.
Can I use Veo 3.1 from Claude Code, Cursor or Codex?
Yes. Connect the Summer MCP server to Claude Code, Cursor, Codex or another MCP client, then ask your agent to generate with summer_generate_video with model: "veo3.1". Setup instructions are at summerengine.com/mcp.
Where do Veo 3.1 results go?
Every generation is saved to your Summer asset library. From there you can download it or bring it into a Summer Engine project.