A clip from words
Text to video does not need a source still.
Image to video turns one still into a short clip.
OpenDescribe a clip and generate it. Grok Imagine and Veo 3.1 show the credits for the resolution and length before the run.
This model does not take a reference image.
Audio is included. This model does not turn it off.
Write a prompt.

Text to video does not ask for a photograph. That is the difference from image to video, which starts from a still. The button on this page shows the credits before it calls the provider.
Image to video starts from a photograph and shows its own credit count. This page starts from the sentence and shows the count for the text model you picked.
The prompt is the source. The model menu is Grok Imagine, Grok Imagine 1.5, and three Veo 3.1 tiers. Duration and resolution change the credit total when the Kie price is per second. Veo stays one price across 4, 6, and 8 seconds at 1080p, because that is how the public price is listed.
A plan or a pack adds credits for jobs that already have a price. A failed run returns its credits.
Text to video does not need a source still.
The sentence covers the subject and the camera move.
The page only offers a length that has a catalog price.
Download it when you want a copy outside the account.
Text to video means a clip that begins as words, with no source photograph. You write the clip, pick a model, and the button shows the credits for the resolution and length you selected.
Image to video is the same kind of clip when the source is a photograph. This page does not ask for a file. A failed run returns the credits it spent.
Video models do not share one price. Resolution and length change the credits, and the button updates before the run. A failed clip returns that spend.
Write the clip, choose the model, then the size, resolution, and duration that model documents. Grok Imagine prices 480p and 720p by the second and includes audio. Veo 3.1 Lite, Fast, and Quality are priced per 1080p video. The button total is that price. A failed run returns the credits.
Subject, motion, and what should stay still.
Video models show credits for the settings on screen.
Those controls change the number on the button.
The result is a short clip. A failed run returns the spend.
A clip from a sentence uses the models on this page. The button shows the credits for the resolution and length you picked. It does not use a made-up count.
If the sentence was really about a picture you have, start on image to video. Credits come from a monthly plan, a yearly plan, or a pack. Monthly credits last a month. Yearly credits last a year. A pack does not expire.
Lite $17 / Plus $33 / Pro $72 — full list on pricing
No. Grok Imagine, Grok Imagine 1.5, and the three Veo 3.1 tiers on this page take the sentence only.
6, 10, and 15 seconds. Grok Imagine 1.5 offers 6, 8, 10, and 15. Both price 480p and 720p by the second, and the audio is included.
16:9 and 9:16, at 1080p. The lengths are 4, 6, and 8 seconds, at one price for that tier.
No. Audio is included in the credits the button already shows. A failed clip returns that spend.