MCP / Models / Image generation
FLUX 3 Image Klein MCP: quick edits at low cost
Black Forest Labs FLUX 3 Image Klein is the compact, fast tier of FLUX 3 Image: new pictures and edits of up to ten references in a few seconds. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use FLUX 3 Image Klein 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/flux-3-image-klein.md. Help me connect the FlyMy.AI MCP to this assistant, then run FLUX 3 Image Klein (flymyai/flux-3-image-klein) for this task: Generate a 9:16 product photo of a red vintage bicycle against a pastel wall with FLUX 3 Image Klein at 4k.
What FLUX 3 Image Klein does
A distilled 5.6B-parameter model built for editing pictures that also draws them from a prompt; in FlyMy.AI's check on 18 November 2026 a 768 px image was ready in about 3 seconds. Send a prompt, and add images (up to ten, the first is the one that is edited) to edit or combine them. resolution is 768sq, 1k (the default), 1.5k, 2k or 4k, and an edit comes out at the size of resolution, not of its first picture. seed, steps (1 to 16, fewer is faster) and output_format (jpeg or png) are optional. It makes one image per request, billed by size tier, and it does not look up the web or make video: FLUX 3 Image checks the web and FLUX 3 Video makes video.
FLUX 3 Image Klein inputs
Every input of flymyai/flux-3-image-klein as its live schema lists them. Returns image (array).
| Input | Type, values and default |
|---|---|
# prompt | string required What to create, or how to change the pictures in images: one instruction per change, naming the pictures by number |
# images | string optional Pictures to edit or combine: up to 10 links (a JSON array or one link) or uploads; the first is the one that is edited. Leave out to create from the prompt alone |
# aspect_ratio | string optional Allowed: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 Default: auto Shape of the image; auto follows the first picture, or the prompt |
# resolution | string optional Allowed: 768sq, 1k, 1.5k, 2k, 4k Default: 1k Billed per image by size: 768sq $0.008, 1k $0.009, 1.5k $0.011, 2k $0.014, 4k $0.036 |
# width | integer optional Allowed: 64 to 6256 Exact width in pixels, 64-6256, sent together with height; replaces resolution and aspect_ratio. Billed at the smallest size tier that covers width x height (up to 16.8 MP) |
# height | integer optional Allowed: 64 to 6256 Exact height in pixels, 64-6256, sent together with width |
# seed | integer optional Allowed: 0 to 4294967295 Fix for repeatable results |
# steps | integer optional Allowed: 1 to 16 Default: 16 Denoising steps, 1-16: fewer is faster |
# output_format | string optional Allowed: jpeg, png Default: jpeg Image file type |
# safety_tolerance | integer optional Allowed: 0 to 4 Default: 2 Content filter: 0 strictest to 4 most permissive |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/flux-3-image-kleinflymyai/flux-3-image-kleinflymyai/flux-3-image-kleinFLUX 3 Image Klein price
From $0.008 per run, depending on resolution, width and height; one image, by size tier: a custom width and height bill the smallest tier that covers them. A run at the default settings costs $0.009. A run costs $0.008 to $0.036, depending on resolution and width and height. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
Call FLUX 3 Image Klein 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/flux-3-image-klein",
"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/flux-3-image-klein/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-image-klein/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'Questions about FLUX 3 Image Klein
Do I need a Black Forest Labs API key for FLUX 3 Image Klein?
No. FLUX 3 Image Klein runs on FlyMy.AI's account, so you need no Black Forest Labs key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does FLUX 3 Image Klein cost?
From $0.008 per run, depending on resolution, width and height; one image, by size tier: a custom width and height bill the smallest tier that covers them. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use FLUX 3 Image Klein 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 red vintage bicycle against a pastel wall with FLUX 3 Image Klein at 4k." Your agent reads the inputs with get_model_schema and runs flymyai/flux-3-image-klein with run_model.
What does FLUX 3 Image Klein need as input?
FLUX 3 Image Klein requires prompt; it also takes 9 optional inputs, each listed on this page with its allowed values and default.
Can I call FLUX 3 Image Klein from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/flux-3-image-klein/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.





