GPT-Image Legacy Versions

For new projects, use GPT-Image-2.5 / 2 (official; gpt-image-2.5-flare for text-to-image, gpt-image-2.5-sunburst for edits) or GPT-Image-2-All (reverse channel, flat $0.03/image). This page keeps the essentials of the legacy versions so existing integrations can troubleshoot and migrate smoothly.

Version Lineup

Model ID	Released	Endpoint	Pricing	Status
`gpt-image-2.5-flare` (snapshot `-2026-09-08`)	Sep 2026	`/v1/images/generations`, `/v1/images/edits`	Input $5.00 / Output $30.00 per M tokens, same as gpt-image-2	Current, speed-first, text-to-image default
`gpt-image-2.5-sunburst` (snapshot `-2026-09-08`)	Sep 2026	`/v1/images/generations`, `/v1/images/edits`	Same as above	Current, quality- and editing-precision-first
`gpt-image-2` (snapshot `-2026-04-21`)	Apr 2026	`/v1/images/generations`, `/v1/images/edits`	Input $5.00 / Output $30.00 per M tokens	Current, previous generation, `quality` up to `high`
`gpt-image-1.5`	Dec 2025	`/v1/images/generations`	Input $5.00 / Output $10.00 per M tokens	Available; upgrade to `gpt-image-2.5-flare` / `sunburst` recommended
`gpt-image-1`	Apr 2025	`/v1/images/generations`, `/v1/images/edits`	Input $2.50 / Output $8.00 per M tokens	Available; upgrade to `gpt-image-2.5-flare` / `sunburst` recommended
`gpt-image-1-mini`	Apr 2025	`/v1/images/generations`	Lower than `gpt-image-1`	Available

Drop-in migration: change model to gpt-image-2 or gpt-image-2-all. Parameters (size / quality / output_format, …) are largely compatible — no structural code changes required.

Common Parameters (Generation)

All legacy versions share the same generation parameters:

Parameter	Description
`model`	`gpt-image-1.5` / `gpt-image-1` / `gpt-image-1-mini`
`prompt`	Image description (up to 1000 chars)
`size`	`1024x1024` / `1536x1024` / `1024x1536` / `auto`
`quality`	`low` / `medium` / `high` / `auto` (the 2.5 series adds `xhigh` / `max`)
`output_format`	`png` (default) / `jpeg` / `webp`
`output_compression`	JPEG/WebP only, 0–100%
`background`	`transparent` / `opaque` / `auto`
`n`	Number of images (1–10)

Quick Example

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

response = client.images.generate(
    model="gpt-image-1.5",  {/* or gpt-image-1 / gpt-image-1-mini */}
    prompt="A professional product photo on white background, soft studio lighting",
    size="1024x1024",
    quality="high"
)

print(response.data[0].url)

Per-Image Pricing Reference

GPT-Image-1 / 1.5 support both token billing and per-image billing — the system automatically picks whichever is cheaper:

GPT-Image-1.5

Quality	1024×1024	1024×1536 / 1536×1024
Low	$0.009	$0.013
Medium	$0.034	$0.050
High	$0.133	$0.200

GPT-Image-1

Quality	1024×1024	1024×1536 / 1536×1024
Low	$0.005	$0.006
Medium	$0.011	$0.015
High	$0.036	$0.052

Per-image figures are reference only. Actual charges follow whichever billing mode (token or per-image) the system determines is cheaper.

Image Editing (`gpt-image-1` only)

gpt-image-1 supports mask-based editing via the /v1/images/edits endpoint:

response = client.images.edit(
    model="gpt-image-1",
    image=open("original.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="A modern glass skyscraper with reflective windows",
    size="1024x1024"
)

Parameter	Description
`image`	Source image, PNG/WebP/JPG, < 50MB each, up to 16 images
`mask`	Mask image — pixels with alpha=0 will be repainted
`prompt`	Description of what to generate in the masked region

For new editing workflows, use GPT-Image-2 Edit (official) or GPT-Image-2-All Edit (reverse, supports up to 16 input images for blending).

Migrating to GPT-Image-2.5 / 2-All

Your need	Recommended target
Stay on official OpenAI endpoint, need precise size/quality control	`gpt-image-2.5-flare` (text-to-image) / `gpt-image-2.5-sunburst` (edits), official
Want predictable flat pricing ($0.03/image), better instruction following	`gpt-image-2-all` (reverse)
Still need mask-based image editing	`gpt-image-2-all` edit endpoint (up to 16 images)

GPT-Image-2.5 / 2 Overview

The three current official models — endpoint and parameters compatible with legacy

GPT-Image-2-All Overview

Reverse channel, flat $0.03/image, faster turnaround

Official vs Reverse Comparison

Side-by-side comparison and selection guide

Basics

Basic API

Image API (Official)

Video API (Official)

Multimodal Understanding API

Text Generation

Audio API (Official)

Retrieval & Safety

Version Lineup

Common Parameters (Generation)

Quick Example

Per-Image Pricing Reference

GPT-Image-1.5

GPT-Image-1

Image Editing (`gpt-image-1` only)

Migrating to GPT-Image-2.5 / 2-All

GPT-Image-2.5 / 2 Overview

GPT-Image-2-All Overview

Official vs Reverse Comparison

​Version Lineup

​Common Parameters (Generation)

​Quick Example

​Per-Image Pricing Reference

​GPT-Image-1.5

​GPT-Image-1

​Image Editing (gpt-image-1 only)

​Migrating to GPT-Image-2.5 / 2-All

GPT-Image-2.5 / 2 Overview

GPT-Image-2-All Overview

Official vs Reverse Comparison

Version Lineup

Common Parameters (Generation)

Quick Example

Per-Image Pricing Reference

GPT-Image-1.5

GPT-Image-1

Image Editing (`gpt-image-1` only)

Migrating to GPT-Image-2.5 / 2-All