xAI

Grok Imagine Video

Generally availableProprietary1K context

Summary

Grok Imagine Video is a proprietary video generation model from xAI, released on 28 Jan 2026. It accepts text, images and video and generates video, with a 1K-token context window.

Image model for prompt-driven generation, editing, and visual design workflows

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperxAI
Release date28 Jan 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window1K (1,024 tokens) [models.dev]
InputText, images and video [models.dev]
OutputVideo [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Grok Imagine Video API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
xAI API
grok-imagine-video
–––1Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
spacexai/grok-imagine-video
––––models.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Grok Imagine Video?

Grok Imagine Video has a context window of 1,024 tokens (1K), according to models.dev.

Is Grok Imagine Video open source?

No. Grok Imagine Video is a proprietary model; xAI has not released its weights. It is available through APIs including xAI API, Vercel AI Gateway.

When was Grok Imagine Video released?

xAI released Grok Imagine Video on 28 Jan 2026, according to models.dev.

Which providers offer Grok Imagine Video?

We track Grok Imagine Video on 2 providers: xAI API, Vercel AI Gateway.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Veo 3.1 Lite GenerateGoogle DeepMind2 Apr 20261K––Closed
Veo 3.1Google DeepMind17 Nov 20251K––Closed
Seedance 2.0ByteDance Seed12 Feb 20264K––Closed
Seedance 2.5ByteDance Seed31 Jul 2026–––Closed
MiniMax H3 MaxMiniMax26 Aug 2026–––Closed
MiniMax H3MiniMax31 Jul 2026–––Open

Change history

  • Now listed on Vercel AI Gateway
  • Input modalities changed from text, image, video, pdf to text, image, video

Sources