OpenAI Image Cloud Image input

GPT Image-2.5 Flare

GPT Image-2.5 Flare: OpenAI's everyday image model. Higher quality than GPT Image-2 at half the latency, free aspect ratios up to 4K, image-to-image editing and transparent backgrounds.

$0.25

per image in the cloud

Use it in Claude or the API

Overview

GPT Image-2.5 Flare is OpenAI's fast, high-quality image model. It delivers sharper detail, more natural lighting and stronger style adherence than GPT Image-2, at about half the latency.

Key Features

Text rendering: reliable typography, labels and layouts
Free aspect ratios: any size up to 4K (3840 px on the long edge)
Image-to-image: edit or restyle a source image while keeping its subject
Transparent backgrounds: clean cut-outs for product shots and stickers

Tips for Best Results

Describe the scene in natural language: subject, setting, lighting, style
Quote any text that must appear in the image between quotation marks
Use a source image with a short prompt describing only what should change

Use it

Three ways to run GPT Image-2.5 Flare

Make an image with GPT Image-2.5 Flare ("gpt-image-2.5-flare"): a lighthouse on a cliff at dusk, cinematic light

curl https://imference.com/generate \
  -H "Authorization: Bearer $IMFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-2.5-flare",
       "format_code": "square",
       "prompt": "a lighthouse on a cliff at dusk, cinematic light"}'

Claude needs the MCP server. API details in the reference.

Specs