xAI

Grok Imagine Image 2.0

Generally availableProprietary64K context

Summary

Grok Imagine Image 2.0 is a proprietary image generation model from xAI, released on 7 Aug 2026. It accepts text and images and generates images, with a 64K-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 date7 Aug 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window64K (64,000 tokens) [models.dev]
InputText and images [models.dev]
OutputImages [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Grok Imagine Image 2.0 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Vercel AI Gateway
spacexai/grok-imagine-image-2.0
–––64Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Grok Imagine Image 2.0?

Grok Imagine Image 2.0 has a context window of 64,000 tokens (64K), according to models.dev.

Is Grok Imagine Image 2.0 open source?

No. Grok Imagine Image 2.0 is a proprietary model; xAI has not released its weights. It is available through APIs including Vercel AI Gateway.

When was Grok Imagine Image 2.0 released?

xAI released Grok Imagine Image 2.0 on 7 Aug 2026, according to models.dev.

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
Muse Image 1.0Meta7 Jul 2026–––Closed
GPT Image 2.5 FlareOpenAI8 Sept 2026–––Closed
GPT Image 2.5 SunburstOpenAI8 Sept 2026–––Closed
FLUX.2 Klein 4BBlack Forest Labs15 Jan 202641K––Open
Qwen-Image-2.1Alibaba (Qwen)14 Sept 20268K––Open
GLM-ImageZhipu AI (Z.ai)14 Jan 202610K––Open

Change history

  • Input modalities changed from text to text, image
  • Input modalities changed from text, image to text
  • Context window changed from 8K to 64K
  • Context window changed from 66K to 8K
  • Input modalities changed from text to text, image

Sources