Models overview
UOVA Studio lists 24 image models and 22 video models, plus 8 audio models and 31 planner models in the Lock-in agent. See how they are listed and priced.
For the complete documentation index, see llms.txt. This page is also available as Markdown.
A model is the AI system that makes your output. In Studio you choose one each time you generate an image or a video. The Lock-in agent also uses chat models to plan your work and audio models to make speech, music and sound.
#The models in Studio today
| Type | How many | Where you use it | Page |
|---|---|---|---|
| Image | 24 | Create Image | Image models |
| Video | 22 | Create Video and Animate a Photo | Video models |
| Audio | 8 | The Lock-in agent only | Audio models |
| Planner (chat) | 31 (Auto plus 30) | The Lock-in agent | Planner models |
Each image and video model has its own page with the maker, the modes it supports, its aspect ratios, its limits and an exact price table. Start with Choosing a model if you are not sure which one fits.
#How the Studio lists a model
The model picker groups models by maker. A model stays in the picker until its retirement date passes, and then the Studio stops listing it. Today one model has a retirement date: GPT Image 1.5, on 2026-12-01.
#What every model shares
- You need to be signed in to generate. Every model is available on every plan, including Free, and credits are the only limit.
- You set Count from 1 to 4 outputs per run. An image run that uses a reference image makes 1 image.
- You can attach one reference image or one start image (JPEG, PNG or WEBP, up to 20 MB).
- The Studio runs exactly the model you chose. If it fails, nothing else is tried in its place and the credits are refunded.
#How credits are priced
Every model has its own credit price, set from what it costs to run. The price rises with the settings that make an output bigger or longer: the aspect ratio on a few image models, the resolution, the length of a clip, and sound on some video models.
Across all settings, an image costs from 6 to 386 credits and a video clip from 147 to 15,442 credits. The Studio shows the exact quote before you generate, and the total is that quote multiplied by Count. See Model pricing for every model, How credits work for allowances and packs, and What actions cost for the other tools.
#What models do not do
- No model takes more than one reference image, an end frame or a video as input. Video upscaling is not available.
- UOVA does not offer 3D model generation, voice cloning, face swap or lip-sync as products.
- Audio models work only inside the Lock-in agent. There is no standalone audio page.