Qwen: Qwen Image 3 Pro

qwen-image-3-pro

images

The larger Qwen Image 3: same text accuracy with richer scene and material detail.

Pricing

Image

Parameters

promptrequired

aspect_ratio1:1 · 1:2 · 1:4 · 2:1 · 2:3 · 3:2 · 3:4 · 4:1 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9

resolution ·

size256x1024 · 1024x256 · 512x1024 · 1024x512 · 576x1024 · 1024x576 · 682x1024 · 1024x682 · 768x1024 · 1024x768 · 818x1024 · 1024x818 · 512x2048 · 1024x1024 · 2048x512 · 1024x2048 · 2048x1024 · 1152x2048 · 2048x1152 · 1364x2048 · 2048x1364 · 1536x2048 · 2048x1536 · 1638x2048 · 2048x1638 · 2048x2048

imageimage-to-image (via /v1/images/edits)

How to use via API

import base64
from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
img = client.images.generate(
    model="qwen-image-3-pro",
    prompt="Милый кот-космонавт на Марсе",
    size="256x1024",  # либо extra_body={"aspect_ratio": "1:1", "resolution": "1k"}
    n=1,
)
with open("image.png", "wb") as f:
    f.write(base64.b64decode(img.data[0].b64_json))

# image-to-image: передать референс(ы) через multipart
edited = client.images.edit(
    model="qwen-image-3-pro",
    image=open("photo.png", "rb"),  # один или несколько референсов
    prompt="Добавь неоновую вывеску на фасад, сохрани композицию",
)
with open("edited.png", "wb") as f:
    f.write(base64.b64decode(edited.data[0].b64_json))

Try in the botAPI docs

Related models

Grok Imagine Image 2.0