What Cosmos 3 Super Image to Video is best at
Pricing
Cosmos 3 Super Image to Video costs 8 credits on Versely. It bills per second of output, so a full job runs 8 to 28 credits depending on clip length.
| Option | Price |
|---|---|
| Price | 4 credits |
Prices are Versely credits. Your plan's credit allowance is on the pricing page.
Specs
- Aspect ratios
- 16:99:161:14:33:4
- Durations
- 2s3s4s5s6s7s
- Qualities
- 480p720p
Inputs
Starting image
Required — you must upload a starting image.
Video input
Not supported.
Release
Cosmos 3 Super Image to Video was released on July 31, 2026 — released 1 months ago.
Compare Cosmos 3 Super Image to Video
Side-by-side pricing, resolution and rankings against models buyers weigh it against.
Other video models
Use Cosmos 3 Super Image to Video inside these tools
Frequently asked questions
How much does Cosmos 3 Super Image to Video cost on Versely?+
Cosmos 3 Super Image to Video costs 8 credits on Versely. A full job runs 8-28 credits depending on clip length.
What is Cosmos 3 Super Image to Video best for?+
Cosmos 3 Super Image to Video is a NVIDIA video model built for image to video.
What resolution does Cosmos 3 Super Image to Video output?+
Cosmos 3 Super Image to Video supports output up to 720p (available qualities: 480p, 720p).
Does Cosmos 3 Super Image to Video need a reference image or video?+
Cosmos 3 Super Image to Video requires a starting image.
When was Cosmos 3 Super Image to Video released?+
Cosmos 3 Super Image to Video was released on July 31, 2026 (released 1 months ago).
Try Cosmos 3 Super Image to Video inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.
Free account. Works in your browser - no install needed. The same account signs in on your phone.
Guides
60+ AI Models, One App: The Complete Versely Model Guide
A practical map of every AI model inside Versely — what each one is best at, when to pick it, and how to route prompts across models for the best result.
One model for image, video and audio?
FLUX 3, MiniMax H3, Wan 3.0 and Gemini Omni Flash train all three modalities at once. When one model beats a best-of-breed stack, and three jobs where it loses.