# Qwen Image 3.0 Pro MCP and API by Alibaba | FlyMy.AI

> Alibaba Qwen Image 3.0 Pro draws and edits images with small crisp text, nested layouts such as newspaper pages and menus, and very fine detail.

Page: https://flymy.ai/mcp/models/qwen-image-3-0-pro/

MCP / Models / Image generation

# Qwen Image 3.0 Pro MCP: dense layouts and fine detail

Alibaba Qwen Image 3.0 Pro draws and edits images with small crisp text, nested layouts such as newspaper pages and menus, and very fine detail. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Qwen Image 3.0 Pro](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#start) [Inputs and price](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#inputs)

No API key, from $0.04 / image, Text and image to image, Alibaba, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Qwen Image 3.0 Pro 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-pro.md. Help me connect the FlyMy.AI MCP to this assistant, then run Qwen Image 3.0 Pro (flymyai/qwen-image-3_0-pro) for this task: Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with Qwen Image 3.0 Pro at 2k.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/qwen-image-3-0-pro.md)

## What Qwen Image 3.0 Pro does

The higher tier of Qwen Image 3.0, with the same inputs: a prompt in Chinese or English, and images (one to three links) to edit. Alibaba says it renders text as small as 10 px in 12 languages, builds nested layouts such as newspaper pages, storyboards, menus and exam sheets in one pass, and shows very fine detail such as pores and hairs. resolution is 1k, the default, or 2k, billed by size tier; an edit with aspect_ratio auto keeps its picture's shape and is usually made at the 2k tier, so name a 1k shape to keep it at the 1k price. size, n, negative_prompt, seed, prompt_extend and watermark work as in Qwen Image 3.0, and each picture you send adds a small charge. It does not make video and takes no mask. Alibaba caps this model at 5 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 Pro inputs

Every input of `flymyai/qwen-image-3_0-pro` as its live schema lists them. Returns `images` (array).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-prompt) `prompt` | string required What to draw, or what to change in the pictures you give. Chinese or English |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-images) `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 |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-resolution) `resolution` | string optional Allowed: 1k, 2k Default: `1k` Size class and price tier: 1k is about 1 megapixel (1024x1024) at $0.04 per image, 2k about 4 (2048x2048) at $0.075 |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-aspect_ratio) `aspect_ratio` | string optional Allowed: auto, 1:1, 16:9, 9:16, 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 |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-size) `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 |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-n) `n` | integer optional Allowed: 1 to 4 Default: `1` How many images to make; each one is billed |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-negative_prompt) `negative_prompt` | string optional What to keep out of the image |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-seed) `seed` | integer optional Allowed: 0 to 2147483647 Fix for repeatable results |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-prompt_extend) `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 |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-watermark) `watermark` | boolean optional Default: `false` Add Alibaba's watermark to the image |
| [#](https://flymy.ai/mcp/models/qwen-image-3-0-pro/#input-enable_safety_checks) `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.

**“Generate a 9:16 product photo of a smartwatch on a mossy rock in soft fog with Qwen Image 3.0 Pro at 2k.”** runs `flymyai/qwen-image-3_0-pro`

**“Make three versions of a poster for a tech meetup about AI agents with Qwen Image 3.0 Pro in one run and send me the links.”** runs `flymyai/qwen-image-3_0-pro`

**“Use Qwen Image 3.0 Pro to place the product from the photo I attach on a marble bathroom counter at sunrise.”** runs `flymyai/qwen-image-3_0-pro`

## Qwen Image 3.0 Pro price

From $0.04 per image, depending on resolution; each picture given to edit adds $0.003. A run at the default settings costs $0.04. A run costs $0.04 to $0.309, depending on resolution and n. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

| Setting | Price |
|---|---|
| resolution 1k | $0.04 per image |
| resolution 2k | $0.075 per image |

[See usage pricing →](https://flymy.ai/pricing/)

## Call Qwen Image 3.0 Pro 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-pro",
  "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-pro/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/qwen-image-3_0-pro/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 Pro

**Do I need an Alibaba API key for Qwen Image 3.0 Pro?**

No. Qwen Image 3.0 Pro 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 Pro cost?**

From $0.04 per image, depending on resolution; 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 Pro 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 Qwen Image 3.0 Pro at 2k." Your agent reads the inputs with get_model_schema and runs flymyai/qwen-image-3_0-pro with run_model.

**What does Qwen Image 3.0 Pro need as input?**

Qwen Image 3.0 Pro 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 Pro from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/qwen-image-3_0-pro/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More image generation models

Text to image: product shots, ads, posters, illustrations and editable vector graphics from a prompt, many with reference images.

### Qwen Image 3.0

Alibaba's Qwen Image 3.0: signs, menus and posters with crisp text, plus edits of up to three pictures.

Text and image to image / $0.03 / image

Link: https://flymy.ai/mcp/models/qwen-image-3-0/

### Wan 2.7 Image Pro

Alibaba's pro image model: up to 4K, nine references, layout boxes and color palettes.

Text and image to image / $0.075 / image

Link: https://flymy.ai/mcp/models/wan-2-7-image-pro/

### Qwen-Image Fast

Alibaba's open Qwen-Image on our GPUs: posters and signs with English or Chinese text.

Text to image / $3.00 / hr

Link: https://flymy.ai/mcp/models/qwen-image-fast/

### Qwen-Image LoRA

Qwen-Image with up to two LoRA adapters: your trained style or character in every image.

Text to image / $0.018 / run

Link: https://flymy.ai/mcp/models/qwen-image-lora-fast/

### FLUX 3 Image

Black Forest Labs' main image model: prompts, edits of up to ten pictures and web-checked subjects.

Text and image to image / from $0.041 / run

Link: https://flymy.ai/mcp/models/flux-3-image/

### FLUX 3 Image Klein

The compact FLUX 3 for quick edits, variations and high-volume work where cost matters.

Text and image to image / from $0.008 / run

Link: https://flymy.ai/mcp/models/flux-3-image-klein/

## Go to the source

[Qwen Image 3.0 Pro in the playground →](https://app.flymy.ai/models/flymyai/qwen-image-3_0-pro), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Image generation guide →](https://docs.flymy.ai/guides/generate-images), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

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.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
