All Models

xAI logo

Grok Imagine Video

Grok Imagine Video generates footage from text or image references, animates still pictures and extends existing clips with a described continuation.

Image to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 6s$0.30 / run
Duration: 10s$0.50 / run
  • Resolution: 720p, 480p (same price).

Reference to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 6s$0.30 / run
Duration: 10s$0.50 / run
  • Images count: 1โ€“7 (same price).
  • Resolution: 720p, 480p (same price).

Text to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 6s$0.30 / run
Duration: 10s$0.50 / run
  • Resolution: 720p, 480p (same price).

Video extension

Price per run for each listed option.

OfferingPrice (USD)
Duration: 6s$0.30 / run
Duration: 10s$0.50 / run

Grok Imagine Video

Grok Imagine Video combines text-driven video generation, still-image animation, reference-guided generation and video extension. A written scene can define footage from scratch; an image can establish the appearance of a shot; reference images can guide a subject's identity and visual style.

For image-based work, the text describes the intended motion while the supplied visuals establish context. With an existing clip, a written continuation guides the added footage. These operations support developing a scene from an initial concept through to a longer moving sequence.

What it's good for

Product teams can animate a photograph or use different views of an item to guide a showcase clip. Illustrators can explore movement in concept artwork, while filmmakers can visualize a scene's action and camera behavior from a written brief.

Extension is useful for continuing an establishing shot or developing a moment beyond its original ending. The combination also suits social content built from existing visual assets and motion studies for production planning.

Model ID

xai/grok-imagine-video

Output Type

Video

Pricing

From $0.30 / run

Provider

xAI

Hosting

Passthru

Grok Imagine Video

Grok Imagine Video combines text-driven video generation, still-image animation, reference-guided generation and video extension. A written scene can define footage from scratch; an image can establish the appearance of a shot; reference images can guide a subject's identity and visual style.

For image-based work, the text describes the intended motion while the supplied visuals establish context. With an existing clip, a written continuation guides the added footage. These operations support developing a scene from an initial concept through to a longer moving sequence.

What it's good for

Product teams can animate a photograph or use different views of an item to guide a showcase clip. Illustrators can explore movement in concept artwork, while filmmakers can visualize a scene's action and camera behavior from a written brief.

Extension is useful for continuing an establishing shot or developing a moment beyond its original ending. The combination also suits social content built from existing visual assets and motion studies for production planning.