← All models

OpenAI: GPT Image 2.6 SunburstNEW

openai/gpt-image-2.6-sunburst
GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.
Modalities
Price
Released
Nov 4, 2026

Parameters

promptrequired, up to 32,000 characters
aspect_ratio1:11:21:32:12:33:13:23:44:34:55:49:1616:921:9
backgroundtransparent · opaque · auto
resolution1k2k4k
size512x15361536x5121024x10241024x17921792x10241024x20482048x10241152x20482048x11521360x20482048x13601024x30721536x20482048x15363072x10241280x25602560x12801632x20482048x16322880x12322048x20481280x38403840x12801920x38403840x19202576x32163216x25762160x38402880x28803840x21602496x33283328x24962368x35523552x23684480x1920
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="openai/gpt-image-2.6-sunburst",
    prompt="Милый кот-космонавт на Марсе",
    size="512x1536",  # 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="openai/gpt-image-2.6-sunburst",
    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