MCP / Models / Image generation
Qwen Image 3.0 MCP: images with crisp text and edits
Alibaba Qwen Image 3.0 draws an image from a prompt or edits one to three of your pictures from a plain instruction; Alibaba lists crisp text in 12 languages. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use Qwen Image 3.0 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/qwen-image-3-0.md. Help me connect the FlyMy.AI MCP to this assistant, then run Qwen Image 3.0 (flymyai/qwen-image-3_0) for this task: Generate a 9:16 product photo of a red vintage bicycle against a pastel wall with Qwen Image 3.0 at 2k.
What Qwen Image 3.0 does
Send a prompt, in Chinese or English, for a new image, or add images (one to three links) and say in the prompt what to change. Alibaba lists crisp text as small as 10 px in 12 languages and dense layouts made in one pass, so it suits signs, menus and posters. resolution is 1k, the default, or 2k; aspect_ratio auto keeps the shape of the first picture in an edit, and size sets an exact width and height; n makes one to four images. prompt_extend is on by default and adds detail to the prompt, but a run at 1k then takes about 35 seconds instead of 5 to 10. Billing is per image made, plus a small charge for each picture you send. It does not make video and takes no mask: describe the change in the prompt. Alibaba caps this model at 20 requests a minute across the platform, so a run in a busy minute can wait, or end with a rate-limit message that is not charged.
Qwen Image 3.0 inputs
Every input of flymyai/qwen-image-3_0 as its live schema lists them. Returns images (array).
| Input | Type, values and default |
|---|---|
# prompt | string required What to draw, or what to change in the pictures you give. Chinese or English |
# images | string optional Up to 3 image URLs to edit (a JSON array or one URL): JPG, PNG, BMP, TIFF, WEBP or GIF, up to 10 MB each. Leave out for a new image |
# resolution | string optional Allowed: 1k, 2k Default: 1k Size class: 1k is about 1 megapixel (1024x1024), 2k about 4 (2048x2048). $0.03 per image at either |
# aspect_ratio | string optional Allowed: auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 Default: auto Shape of the result. auto: an edit keeps the shape of its first picture (Alibaba picks the size, usually the 2k tier) and a new image is square; name a shape to fix the size by resolution |
# size | string optional Exact size as WIDTHxHEIGHT, such as 1536x1024; wins over resolution and aspect_ratio. 512x512 to 2048x2048 pixels in all, at most 8:1; up to 2.25 megapixels (1500x1500) bills as 1k, larger as 2k |
# n | integer optional Allowed: 1 to 4 Default: 1 How many images to make; each one is billed |
# negative_prompt | string optional What to keep out of the image |
# seed | integer optional Allowed: 0 to 2147483647 Fix for repeatable results |
# prompt_extend | boolean optional Default: true Let Alibaba add detail to the prompt before it draws. A run takes about 35 s with it and 5-10 s without |
# watermark | boolean optional Default: false Add Alibaba's watermark to the image |
# enable_safety_checks | boolean optional Default: true Alibaba content inspection of the prompt, the pictures and the result; false asks Alibaba to skip it and turns prompt rewriting off too |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/qwen-image-3_0flymyai/qwen-image-3_0flymyai/qwen-image-3_0Qwen Image 3.0 price
$0.03 per image; each picture given to edit adds $0.003. A run at the default settings costs $0.03. A run costs $0.03 to $0.129, depending on resolution and n. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| Any | $0.03 per image |
Call Qwen Image 3.0 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/qwen-image-3_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/qwen-image-3_0/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/qwen-image-3_0/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=A ceramic mug on a sunlit kitchen counter, product photo'Questions about Qwen Image 3.0
Do I need an Alibaba API key for Qwen Image 3.0?
No. Qwen Image 3.0 runs on FlyMy.AI's account, so you need no Alibaba key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does Qwen Image 3.0 cost?
$0.03 per image; each picture given to edit adds $0.003. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use Qwen Image 3.0 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 red vintage bicycle against a pastel wall with Qwen Image 3.0 at 2k." Your agent reads the inputs with get_model_schema and runs flymyai/qwen-image-3_0 with run_model.
What does Qwen Image 3.0 need as input?
Qwen Image 3.0 requires prompt; it also takes 10 optional inputs, each listed on this page with its allowed values and default.
Can I call Qwen Image 3.0 from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/qwen-image-3_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.





