← Models

grok-imagine-video

xAI · Grok Imagine

xAI's Grok Imagine video model for text-to-video, image-to-video, video editing, and short creative clips.

Part of Grok Imagine family · Other versions: grok-imagine-image-quality , grok-imagine-image , grok-imagine-image-1212 , grok-imagine-video-1212
Type
video
Context
N/A
Max Output
N/A
Status
current
API Access
Yes
License
proprietary
video-generation video-editing image-to-video xai api grok-imagine creative
Released January 2026 · Updated May 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on May 8, 2026.

grok-imagine-video is xAI’s current Grok Imagine video model for API workflows. It covers text-to-video, image-to-video animation, video editing, reference-to-video, and video extension patterns through asynchronous requests.

This replaces the older 1212-era naming in public-facing Signal Lens copy and gives readers the current model ID to test.

Capabilities

xAI’s video APIs can generate, edit, and extend short videos with Grok video models. The current docs emphasize image-to-video animation, video editing that preserves the rest of the scene, reference-to-video generation, and manual or SDK-managed polling for async completion.

That makes the model useful for campaign motion concepts, social clips, product visualization, and visual prototyping where a team wants xAI-native media generation next to Grok reasoning.

Technical Details

This is a video-native model, so token-style context and max-output fields are represented as 0 in this content system and should be interpreted as N/A in UI views.

Current xAI docs list:

  • Model name: grok-imagine-video
  • Regions: us-east-1, eu-west-1
  • Maximum generation duration: 15 seconds
  • Maximum video-editing input length: 8.7 seconds
  • Extension input duration: 2 to 15 seconds
  • Output resolution options include 480p and 720p pricing tiers

Pricing & Access

Published xAI pricing:

  • Video output at 480p: $0.05 per second
  • Video output at 720p: $0.07 per second
  • Image input: $0.002 per image
  • Video input for extension/editing: $0.01 per second

Access is through xAI’s video APIs. Requests are asynchronous: start a request, poll with the returned request ID, then use the completed video URL when it is ready.

Best Use Cases

Use grok-imagine-video for short motion concepts, social ad variants, image-to-video exploration, product showcase clips, and Grok-centric creative workflows where API integration matters.

For production-grade cinematic video, benchmark against Sora, Veo, Runway, and Pika with your actual shot requirements before committing.

Comparisons

  • Sora 2 (OpenAI): Strong OpenAI-native video model family with broader ChatGPT ecosystem visibility.
  • Veo 3.1 (Google): Strong Google/Vertex video route for teams already on Google Cloud.
  • Runway and Pika: Creator-tool ecosystems with workflow affordances beyond raw model API access.