xAI: Grok Imagine Image 2.0

x-ai/grok-imagine-image-2.0

images

An image generation and editing model from xAI: creating images from text prompts and editing images from references, with low and medium quality modes.

Price

Released

Aug 11, 2026

Parameters

promptrequired, up to 8,000 characters

aspect_ratio1:11:22:12:33:23:44:39:1616:9

resolution1k2k

size706x14141414x706816x12241224x816750x13321332x750866x11541154x8661000x10001024x20482048x10241152x20482048x11521364x20482048x13641536x20482048x15362048x2048

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="x-ai/grok-imagine-image-2.0",
    prompt="Милый кот-космонавт на Марсе",
    size="706x1414",  # 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="x-ai/grok-imagine-image-2.0",
    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))

API docsTry in the bot

Related models