Grok Imagine Image 2.0. xAI images and edits in seconds.
xAI's image model makes a picture from a prompt, or edits from up to three reference images, at 1K or 2K in thirteen aspect ratios.
- Text and image input
- 1K or 2K
- 13 aspect ratios plus auto
- Up to 3 reference images
Grok Imagine Image 2.0 is xAI's image generation and editing model. Give it a prompt, or a prompt plus up to three reference images, and pick 1K or 2K. It offers thirteen aspect ratios, from 9:20 portraits to 20:9 banners.
In our tests a 1K square came back in 11 seconds and billed 4 cents, and an edit with one reference came back in 7 seconds and billed 7 cents. The edit kept the product and moved it into the new set. On Treza it sits in the Image Generation node's model picker. It bills from prepaid credits, and a failed generation costs nothing.
Back in seconds
7 to 11 seconds per image in our tests, quick enough to iterate on a prompt in one sitting.
Edits from references
Attach up to three images and describe the change. Our one-reference edit kept the product and placed it in a new scene.
Thirteen aspect ratios
From 9:20 and 9:16 portraits to 16:9 and 20:9 banners, plus auto, so one model covers stories, thumbnails and headers.
Low cost per image
OpenRouter lists 4 to 8 cents per image by resolution and quality, plus a cent per reference image.
What to make with Grok Imagine Image 2.0
Real prompts, and what comes back. Every one runs as a node on the Treza canvas.
“A ceramic cup of coffee on a sunlit wooden cafe table, steam rising, shallow depth of field”
A warm product-style still.
“The same folded shirt (attached) on a white marble counter in a bright studio”
Your product moved into a new set.
“A 16:9 thumbnail background of a neon city street at night, empty center for text”
A wide backdrop with room for a title.
“A 9:16 poster of a lone astronaut on a red desert, dramatic sky”
A vertical still for stories and Shorts.
“Put this mug (attached) on a picnic blanket in a summer park”
A lifestyle shot from a plain product photo.
“A 2K flat lay of stationery on a pastel desk, top down”
A clean overhead still at the higher resolution.
Grok Imagine Image 2.0 is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Grok Imagine Image 2.0
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Grok Imagine Image 2.0 as an API, priced per image
The Grok Imagine Image 2.0 API
Build a pipeline with Grok Imagine Image 2.0 on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Grok Imagine Image 2.0 pricing
Prepaid credits, no subscription. Each image is charged at Grok Imagine Image 2.0's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Grok Imagine Image 2.0, answered
What does Grok Imagine Image 2.0 cost?
OpenRouter lists 4 cents at 1K and 6 at 2K on low quality, 6 and 8 on medium, plus a cent per reference image. Our 1K test billed 4 cents, and an edit with one reference 7 cents. Treza quotes the price before a run and bills from prepaid credits.
How many reference images can I use?
Up to three. Wire them into the Image Generation node's reference input and describe how they should be used.
How is it different from Grok Imagine video?
Grok Imagine Image 2.0 makes stills. Grok Imagine and Grok Imagine 1.5 make video clips. A common pipeline makes a still with this model and wires it into a video node's First frame port to animate it.
How much does Grok Imagine Image 2.0 cost on Treza?
Treza uses prepaid credits with no subscription. Each image is charged at Grok Imagine Image 2.0's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Grok Imagine Image 2.0 through an API?
Yes. Build a pipeline that uses Grok Imagine Image 2.0 and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.