Pricing

Video to video

Video to video, from every model that takes a clip.

You stop starting from a blank prompt. Your own footage goes in. Prices are on the cards.

Restyle your own clip

The definition

What is video-to-video AI?

Video-to-video AI is a render whose input is footage rather than a blank prompt. You attach a clip, describe what should change, and the model returns a new take built on the motion already there. Some of these models want a clip and nothing else will do. Others take a still instead, or read a clip as an optional extra beside the prompt. Each card below says which, and what a render costs.

The roster

Every model that reads your footage.

Read what it wants and what it costs. Then open the page.

Kling O1

Kuaishou

Multi-reference omni model — motion transfer and clip editing.

Clip input
Optional
Max length
10s
Resolutions
720p / 1080p

from ⚡77$0.77 at pack rate

Open the model page

MiniMax H3 Max (reference-to-video)

MiniMax

Up to 9 references cited by position in the prompt (Image 1, Video 1…).

Clip input
A still or a clip
Max length
15s
Resolutions
480P / 768P

from ⚡8$0.08 at pack rate

Open the model page

Wan 2.7 (image-to-video)

Alibaba

Animate a first frame — or bridge to a last one.

Clip input
A still or a clip
Max length
15s
Resolutions
720P / 1080P

from ⚡41$0.41 at pack rate

Open the model page

Runway Aleph 2

Runway

Video-to-video restyling — bring your own clip.

Clip input
A clip, required
Max length
30s

⚡3/s$0.03/s at pack rate

Open the model page

Three moves

Your clip to a new take.

01

Pick the model

Choose from the roster above. The card shows its price.

02

Attach the footage

Drop in the clip you want rebuilt.

03

Write and render

The exact price sits on the button. Press it once.

Start from footage you already shot

Most generated video begins with a blank prompt and invents everything. That is the wrong tool when the performance already exists on your drive: the timing is right, the framing is right, and what you want changed is the look. The models below take the clip itself as the input, so the motion survives the render. What this page adds is the shortlist. Instead of opening every model page to find out which ones accept footage, you read one roster the platform catalog writes.

What the roster is, and where it comes from

Every model here qualified by the same gate the composer and the workflow runner use before they will hand a clip over. That gate is deliberately narrow. Several image-to-video models say media is required and mean a photograph, and their request schemas reject a video outright, so listing them would sell a failed render. Length ceilings and resolutions come from the same feed.

Each card says what it wants

A model that will not render without footage is not the same as one that reads a clip as an optional extra, and a model that will take a still instead is a third thing. Every card carries that row because the difference decides whether you can press Generate at all, and the composer enforces the same rule before it spends anything.

The price is visible before you spend

Each card carries a floor price in credits and the same figure in dollars at the pay-as-you-go pack rate. A model that bills per second of output rather than per clip says so on the figure itself. The binding quote is still the one on the Generate button, computed for the exact length and tier you picked.

Questions

Frequently asked questions

The roster on this page is the answer, and it is read from the platform catalog rather than written down. Every model listed accepts footage on the wire, and each card names the vendor behind it, what it wants attached, the longest clip it will carry and the price of a render. A model that gains a clip input joins this page on the next catalog refresh.

Image-to-video animates a still: one picture goes in and motion is invented around it. Video-to-video starts from motion that already exists, so the timing, the framing and the performance in your footage carry through. Several models on OpenClips do the first job and reject a clip outright at dispatch, which is why they are not carded here.

It depends on the model, and each card states its own rule rather than a shared one. Some will not render without footage, so the composer blocks the press until you attach it. Others take a still instead, or read a clip as an optional extra beside your prompt. The model page for each carries the full behaviour.

The length ceiling on each card is the longest render that model will carry, read from the same feed the composer reads. Your source footage is bounded by the upload limits in the app rather than by a figure on this page. Read the model page before you plan an edit around a specific runtime.

Free to try. A new account gets a one-time credit grant and no card is asked for. Packs start at $10/1,000⚡. Video costs more than stills, so the grant is there to judge the output rather than to fund a campaign.

Rebuild a clip you already have

Pick a model. Attach the footage. Press once.

Restyle your own clip

The price is on the button before you press it.