MCP / Models / Image generation
Grok Imagine Image 2.0 MCP: images and edits up to 2K
xAI Grok Imagine Image 2.0 draws an image from a prompt, or edits and combines one to five of your pictures, at 1k to 2k. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Grok Imagine Image 2.0 in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/grok-imagine-image-2-0.md. Help me connect the FlyMy.AI MCP to this assistant, then run Grok Imagine Image 2.0 (flymyai/grok-imagine-image-2_0) for this task: Generate a 9:16 product photo of a ceramic coffee mug on a sunlit kitchen counter with Grok Imagine Image 2.0 at 2k.
What Grok Imagine Image 2.0 does
Send a prompt for a new image; xAI advises opening it with the subject: what it is, its form and the setting. Add images (one to five links) to edit or combine them, and with several name them in the prompt as IMAGE_0, IMAGE_1 and so on, each in angle brackets. resolution is 1k (the default), 1.5k or 2k, and quality is low, the default, or medium for finer detail. aspect_ratio is auto, where a new image gets the shape that suits the prompt and an edit keeps the shape of its picture, or one of 15 shapes; n makes one to ten images. Results are JPEG files. Each image made is billed, and each picture you send adds a small charge once per request. It does not make video, which Grok Imagine Video 1.5 does, and takes no mask.
Grok Imagine Image 2.0 inputs
Every input of flymyai/grok-imagine-image-2_0 as its live schema lists them. Returns image (array).
| Input | Type, values and default |
|---|---|
# prompt | string required What to draw, or what to change in the pictures you give |
# images | string optional Up to 5 image URLs to edit (a JSON array or one URL): JPEG, PNG or WEBP. Leave out for a new image. With several, name them in the prompt as IMAGE_0, IMAGE_1 and so on, each in angle brackets |
# aspect_ratio | string optional Allowed: auto, 1:1, 3:4, 4:3, 9:16, 16:9, 2:3, 3:2, 9:19.5, 19.5:9, 9:20, 20:9, 1:2, 2:1, 21:9, 5:2 Default: auto Shape of the result. auto: a new image gets the shape that suits the prompt and an edit keeps the shape of its picture. With a single picture the shape is always the picture's |
# resolution | string optional Allowed: 1k, 1.5k, 2k Default: 1k Size class, billed per image with the quality: low $0.04 at 1k, $0.05 at 1.5k, $0.06 at 2k; medium $0.06, $0.07, $0.08 |
# quality | string optional Allowed: low, medium Default: low low is xAI's cheaper setting; medium spends more compute on each image for finer detail and costs $0.02 more per image |
# n | integer optional Allowed: 1 to 10 Default: 1 How many images to make; each one is billed |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/grok-imagine-image-2_0flymyai/grok-imagine-image-2_0flymyai/grok-imagine-image-2_0Grok Imagine Image 2.0 price
From $0.04 per image, depending on quality and resolution; each picture given to edit adds $0.01. A run at the default settings costs $0.04. A run costs $0.04 to $0.85, depending on quality and resolution and n. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| quality low, resolution 1k | $0.04 per image |
| quality low, resolution 1.5k | $0.05 per image |
| quality low, resolution 2k | $0.06 per image |
| quality medium, resolution 1k | $0.06 per image |
| quality medium, resolution 1.5k | $0.07 per image |
| quality medium, resolution 2k | $0.08 per image |
Call Grok Imagine Image 2.0 from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/grok-imagine-image-2_0",
"input": {
"prompt": "A ceramic mug on a sunlit kitchen counter, product photo"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/grok-imagine-image-2_0/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/grok-imagine-image-2_0/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'Questions about Grok Imagine Image 2.0
Do I need an xAI API key for Grok Imagine Image 2.0?
No. Grok Imagine Image 2.0 runs on FlyMy.AI's account, so you need no xAI key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Grok Imagine Image 2.0 cost?
From $0.04 per image, depending on quality and resolution; each picture given to edit adds $0.01. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Grok Imagine Image 2.0 in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Generate a 9:16 product photo of a ceramic coffee mug on a sunlit kitchen counter with Grok Imagine Image 2.0 at 2k." Your agent reads the inputs with get_model_schema and runs flymyai/grok-imagine-image-2_0 with run_model.
What does Grok Imagine Image 2.0 need as input?
Grok Imagine Image 2.0 requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.
Can I call Grok Imagine Image 2.0 from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/grok-imagine-image-2_0/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





