VEO 3.1 The Next Leap in Generative Video
Veo 3.1 is an upgrade of Google’s Veo 3 model. It can combine multiple elements in one video, extend existing clips, create videos from start and end images, while maintaining stunning audiovisual quality. Veo 3.1 is available in MakeFun AI video generator now.
How To Use Veo 3.1 AI Video Model on MakeFun AI
01
Upload Image
Add the reference image to shape your creation
02
Write your scenario
Describe desired Results, Veo 3.1 supports video generation with advanced prompt understanding
03
Generate Video
Click the button and obtain high-quality video instantly. Output video support 480p, 720p and 1080p resolution formats.
See the Power of Google Veo 3.1
A platform trusted by one million creators
Ethan Miller
★★★★★
Just jump in and start creating! With MakeFun AI Head Swap, you can instantly put your head on any celebrity, model, or movie character. From realistic portraits to AI cartoon swaps, Veo 3.1 makes it super easy, fun, and ultra-realistic.
Ava Mitchell
★★★★★
Saved me so much time. I had to throw together an important pitch last minute, and normally I’d be up all night. But with MakeFun, I knocked it out in a couple hours and still had energy to spare.
Mason Turner
★★★★★
One client even asked how big my team was. Truth is, it was just me using MakeFun — I got a project done in three days instead of a week. It basically saved us a whole creative department’s worth of work.
Caleb Parker
★★★★★
I used to stick to small branding projects. But with MakeFun, I can tackle bigger ones — and actually scale them. Now I feel confident taking on large jobs because I know I can deliver on time.
Why choose MakeFun?
Great Value, One Price for All
Pay once, and unlock access to a wide range of powerful AI features — no need to pay per generation. Whether it’s video creation, voice cloning, or image processing, everything is included. Create more, spend less.
High-Quality Results That Impress
Powered by MakeFun’s industry-leading technology our tools deliver natural, realistic, and detailed outputs. From visuals to audio, every result is crafted to match professional standards.
Unlimited Generation, Limitless Creativity
No usage limits — generate as much as you want, whenever you want. Experiment with styles, iterate freely, and bring all your creative ideas to life without worrying about running out of credits. Your creativity never hits a wall.
Veo 3.1 Vertex AI cost worksheet
Source refresh: July 10, 2026. Google Cloud currently lists Veo 3.1, Veo 3.1 Fast, and Veo 3.1 Lite as separate Vertex AI video routes. Use the current model documentation and pricing table before quoting a final budget, because launch stage, 4K availability, quota, endpoint migration, and per-second prices can change.
| Planning row | Current Vertex AI inputs | Makefun handoff |
|---|---|---|
| 4-second draft clip | Model docs support 4, 6, or 8 second outputs and up to four output videos per prompt. Pricing rows to compare: Veo 3.1 video-only at $0.20/second for 720p or 1080p, Fast video-only at $0.08/second for 720p and $0.10/second for 1080p, and Lite video-only at $0.03/second for 720p and $0.05/second for 1080p. | Use direct Vertex AI when the team needs API control and can absorb retries. Use Makefun when the goal is fast creator iteration without managing returned-output multipliers. |
| 8-second product teaser with audio | Separate video-only from video-plus-audio. Current pricing lists Veo 3.1 video-plus-audio at $0.40/second for 720p or 1080p, Fast at $0.10/second for 720p and $0.12/second for 1080p, and Lite at $0.05/second for 720p and $0.08/second for 1080p. | Budget each returned output, then divide by approved clips. Move to Makefun when review, prompt iteration, image-to-video setup, or social export matters more than raw API routing. |
| 4K hero-video test | Current pricing lists 4K rows for Veo 3.1 and Veo 3.1 Fast: standard video-plus-audio $0.60/second, standard video-only $0.40/second, Fast video-plus-audio $0.30/second, and Fast video-only $0.25/second. Confirm 4K support and quota immediately before production use. | Treat 4K as a higher-risk test row. Keep a fallback route ready when preview status, quota, brand review, or approval rate makes direct API output too expensive. |
Do not compare Veo routes by clip duration alone. The worksheet should multiply output seconds by returned videos, retries, audio branch, resolution, and approval rate, then compare that cost with a Makefun AI video or image-to-video workflow for the same creative job.
FAQ
- What kind of videos can I create?
You can create anything from cinematic short films and animated characters to product visualizations and abstract visual art. If you can describe it, Veo 3.1 can aim to create it.
- What is Veo 3.1?
Veo 3.1 is the next major version of Open Sora text-to-video model, a generative AI that creates realistic and imaginative video scenes from text instructions. It features significant improvements in realism, consistency, length, and user control.
- How is Veo 3.1 different from the first version?
Veo 3.1 introduces higher fidelity, better physics simulation, longer video generation capabilities, and advanced creative controls that allow users to direct the final output more precisely.
- When did Veo 3.1 release?
Users can start generate Veo 3.1 starting on September 1, 2025.