MCP / Models / Image generation

Krea 3 MCP: pictures of up to 4 megapixels with no API key

Krea 3 turns a prompt into a finished picture of up to about 4 megapixels, with a prompt expander that writes a fuller brief first. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API keyfrom $0.0063 / runText to imageKreaCommercial use
Krea 3 sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Krea 3 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/krea-3-text-to-image.md. Help me connect the FlyMy.AI MCP to this assistant, then run Krea 3 (flymyai/krea-3-text-to-image) for this task: Generate a product photo of a glass perfume bottle on black volcanic sand with Krea 3.
Open FlyMy.AIDownload brief

What Krea 3 does

Describe the picture in prompt, up to 5,000 characters, and a short prompt works: an expander rewrites it into a fuller brief before the model draws, and reasoning_level (medium, or high for a slower, more careful brief) sets its effort. image_size is auto, the default, where the model chooses the shape and draws at about 2,048 x 2,048 pixels, or one of six shapes: square_hd, square, portrait_4_3, landscape_4_3, portrait_16_9 and landscape_16_9. negative_prompt lists what to keep out, seed fixes the random start and output_format is png (the default) or jpeg. Outputs: images, seed and expanded_prompt, the prompt after expansion.

It is billed per megapixel of the picture, so the shape you pick sets the price, and the price shown before the run is an upper bound held on your balance. It does not edit a picture you send (Krea 3 Edit does), take a custom width and height or make video.

Krea 3 inputs

Every input of flymyai/krea-3-text-to-image as its live schema lists them. Returns images (array), seed (string), expanded_prompt (string).

InputType, values and default
# prompt
string required What to draw: the subject, the scene, the light and the style, up to 5,000 characters
# image_size
string optional Allowed: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 Default: auto auto (the default): the model chooses the shape and draws at about 2,048 x 2,048 pixels, 4 megapixels, the most it makes; or a shape: square_hd (1024 x 1024), square, portrait_4_3, landscape_4_3, portrait_16_9 or landscape_16_9. Billed per megapixel: auto about $0.10 for the result, square_hd $0.025, the 4:3 shapes $0.019, the 16:9 shapes $0.014, square $0.006
# reasoning_level
string optional Allowed: medium, high Default: medium How much effort the prompt expander spends on your prompt: medium, high (each slower than the one before); the price is per megapixel at every level
# negative_prompt
string optional What to keep out of the picture, up to 1,024 characters
# seed
integer optional Allowed: 0 to 2147483647 A number that fixes the random start, to repeat or to vary a result; left out, one is chosen
# output_format
string optional Allowed: png, jpeg Default: png png (default, lossless) or jpeg (smaller files); the same price

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Generate a product photo of a glass perfume bottle on black volcanic sand with Krea 3.”runs flymyai/krea-3-text-to-image
“Make three versions of a poster for a coffee shop opening with Krea 3 and send me the links.”runs flymyai/krea-3-text-to-image
“Create a 1970s travel poster illustration of a paper airplane flying over a city at dusk with Krea 3.”runs flymyai/krea-3-text-to-image

Krea 3 price

From $0.0063 per run, depending on image_size. A run at the default settings costs about $0.101. A run costs $0.0063 to $0.101, depending on image_size. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

Call Krea 3 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/krea-3-text-to-image",
  "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/krea-3-text-to-image/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/krea-3-text-to-image/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'

Questions about Krea 3

Do I need a Krea API key for Krea 3?

No. Krea 3 runs on FlyMy.AI's account, so you need no Krea key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Krea 3 cost?

From $0.0063 per run, depending on image_size. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use Krea 3 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 product photo of a glass perfume bottle on black volcanic sand with Krea 3." Your agent reads the inputs with get_model_schema and runs flymyai/krea-3-text-to-image with run_model.

What does Krea 3 need as input?

Krea 3 requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

Can I call Krea 3 from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/krea-3-text-to-image/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.