← All models
Microsoft: MAI-Image 2.5
microsoft/mai-image-2.5images
Microsoft's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
Price in / out
Price
≈ 7,32 ₽ per image
Context
4.1K
Released
Jun 2, 2026
Parameters
promptrequired, up to 20,000 charactersaspect_ratio1:12:33:23:44:39:1616:9imageimage-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="microsoft/mai-image-2.5",
prompt="Милый кот-космонавт на Марсе",
# размер задаёт aspect_ratio (у модели нет size-ручки): extra_body={"aspect_ratio": "1:1"}
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="microsoft/mai-image-2.5",
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))
