MCP / Models / Image generation

MiniMax H3 Image MCP: 4K images and edits of 16 pictures

MiniMax H3 Image draws an image from a prompt, or edits and combines up to 16 of your pictures, at up to 4K in any shape from 1:3 to 3:1. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API keyfrom $0.0229 / imageText and image to imageMiniMaxCommercial use
MiniMax H3 Image sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use MiniMax H3 Image 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/minimax-h3-image.md. Help me connect the FlyMy.AI MCP to this assistant, then run MiniMax H3 Image (flymyai/minimax-h3-image) for this task: Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with MiniMax H3 Image at 4K.
Open FlyMy.AIDownload brief

What MiniMax H3 Image does

MiniMax released H3 Image in November 2026 as an open-weight model of its H3 family. Send a prompt for a new image, or add images (up to 16 links, called image 1, image 2 and so on in the prompt) to edit or combine them from a plain instruction. resolution is 1K (the default), 2K or 4K; aspect_ratio is auto, which lets MiniMax choose from your prompt and pictures, or a shape from 1:3 to 3:1; n makes one to ten images and output_format is jpeg, png or webp. MiniMax rewrites the prompt before it draws, always for an edit, and may add details of its own; disable_prompt_enhanced sends your words as they are on a new image. Billing follows the tokens MiniMax reports: the image made, the longer text it writes and each picture you send. It takes no mask, seed or negative prompt, and makes no transparent backgrounds and no video.

MiniMax H3 Image inputs

Every input of flymyai/minimax-h3-image as its live schema lists them. Returns image (array).

InputType, values and default
# prompt
string required What to draw, or what to change in the pictures you give (call them image 1, image 2 ... in order). Up to 32,000 characters; MiniMax rewrites it before it draws
# images
string optional Up to 16 image URLs to edit or combine (a JSON array or one URL): JPEG, PNG, WebP, HEIC or HEIF, each side 128-8192 px, at most 4:1. Leave out for a new image. Each picture adds input tokens: $0.003 at 1 megapixel, $0.008 at 4
# aspect_ratio
string optional Allowed: auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21, 3:1, 1:3 Default: auto Shape of the result: auto lets MiniMax pick it from your prompt and pictures, or a ratio from 1:3 to 3:1
# resolution
string optional Allowed: 1K, 2K, 4K Default: 1K Size class and price tier: 1K is about 1 megapixel (1024x1024), 2K about 4 (2048x2048), 4K about 16 (4096x4096). About $0.023 per image at 1K or 2K, $0.070 at 4K
# n
integer optional Allowed: 1 to 10 Default: 1 How many images to make; each one is billed
# output_format
string optional Allowed: jpeg, png, webp Default: jpeg File type of the images: jpeg is the smallest, png lossless. The price is the same
# disable_prompt_enhanced
boolean optional Default: false Send your prompt to the model as it is, without MiniMax's rewrite: the shape is 1:1 unless you name one, and the text of the rewrite is saved (up to about $0.007 per image). MiniMax then reads only about the first 4,096 tokens of the prompt. Not for edits, which always use the rewrite

Ask your agent

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

“Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with MiniMax H3 Image at 4K.”runs flymyai/minimax-h3-image
“Make three versions of a poster for a tech meetup about AI agents with MiniMax H3 Image in one run and send me the links.”runs flymyai/minimax-h3-image
“Use MiniMax H3 Image to place the product from the photo I attach on a marble bathroom counter at sunrise.”runs flymyai/minimax-h3-image

MiniMax H3 Image price

From $0.0229 per image, depending on resolution; billed by MiniMax's tokens: image output $3.80 per 1M, text input $2.30 per 1M (the prompt and MiniMax's prompt enhancement), each picture given to edit $1.50 per 1M (up to about $0.0078 for a picture of 4 megapixels). A run at the default settings costs $0.0229. A run costs $0.0229 to $0.821, depending on resolution and n. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

SettingPrice
resolution ['1K', '2K']$0.0229 per image
resolution 4K$0.0696 per image

Call MiniMax H3 Image 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/minimax-h3-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/minimax-h3-image/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-h3-image/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'

Questions about MiniMax H3 Image

Do I need a MiniMax API key for MiniMax H3 Image?

No. MiniMax H3 Image runs on FlyMy.AI's account, so you need no MiniMax key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does MiniMax H3 Image cost?

From $0.0229 per image, depending on resolution; billed by MiniMax's tokens: image output $3.80 per 1M, text input $2.30 per 1M (the prompt and MiniMax's prompt enhancement), each picture given to edit $1.50 per 1M (up to about $0.0078 for a picture of 4 megapixels). There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use MiniMax H3 Image 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 smartwatch on a mossy rock in soft fog with MiniMax H3 Image at 4K." Your agent reads the inputs with get_model_schema and runs flymyai/minimax-h3-image with run_model.

What does MiniMax H3 Image need as input?

MiniMax H3 Image requires prompt; it also takes 6 optional inputs, each listed on this page with its allowed values and default.

Can I call MiniMax H3 Image from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/minimax-h3-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.