OpenAI

GPT Image 2

OpenAIToken-based
Alias:gpt-image-2
Create API Key

Compare gpt-image-2 API pricing, supported endpoints, capabilities and access options on Modelsell.

文生图图像编辑商品视觉文字渲染
Starting price
Input / Output · 1M
Context
—
Maximum input window
Modalities
→
Released
Apr 2026

Pricing by Supplier

OpenAI
-40%
Openai官方接口
Input$8$4.8/ 1M
Output$30$18/ 1M
GPT官+AZ 混合
-40%
适合生产环境,az 和官 key 混合渠道
Input$8$4.8/ 1M
Output$30$18/ 1M
标准按次
图片音频视频等多模态按次计费
Input$8/ 1M
Output$30/ 1M
优质按次
Input$16/ 1M
Output$60/ 1M

Capabilities / Supported modalities

Vision
Input
Output

Provider & data privacy

Provider
OpenAIDocs
Tokenizer
o200k_base
License
Proprietary (commercial)Proprietary
Data retention30 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·GPT Image 2

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About GPT Image 2

想把一段设计想法直接变成图片,或把现有图片改成更适合发布的样子,GPT Image 2 都可以作为创作起点。它能理解较完整的文字要求,也接受图像参考,适合把商品外观、人物关系、光线、构图与画面内文字一并安排,而不仅仅生成一种泛泛的风格。

从文字到可用的视觉方案

你可以描述场景中有哪些主体、彼此怎样摆放、镜头从什么角度看,以及观众应该先注意哪里。制作海报时,把标题逐字写出,并说明文字位置、视觉层级和留白;制作插画时,则可以交代人物动作、故事关系与色彩气氛。较复杂的画面应先确定主要内容,再逐步增加装饰,避免每个元素都争夺注意力。

把参考图变成新的设计

参考图编辑适合更换商品背景、调整局部、重组画面或尝试新的视觉表达。模型以高保真图像理解为基础,帮助延续输入中的重要细节。清晰的主体图片与明确的保留要求尤其重要;包装小字、人物面部、精密结构和品牌标识,仍需要在结果中逐项检查。

灵活尺寸让它能够用于横幅、封面、方形商品图等不同构图。透明背景是预览能力,适合需要继续拼贴或网页叠加的素材;应选择能保留透明信息的 PNG 或 WebP,JPEG 会失去透明通道。已经满意的设计,建议每轮只改一个部分,并保留原图作为比较基准,让后续调整更可控。

Use cases and prompting

把陶瓷杯实拍改成新品海报

使用参考图中的白色陶瓷杯,保留杯柄、杯口和釉面纹理。制作横版海报,杯子位于左侧,暖灰色背景,柔和侧光;右侧标题只写“晨光系列”,下方保留空白。不添加其他商品、品牌或英文文字。

如果第一版布局满意,再单独调整标题大小或背景色,避免同时重做主体与版面。

产品图和纯文字创作怎么选? 有准确外观要求时提供清晰商品图;探索概念、插画或氛围时,可以先用文字找方向。

为什么透明背景另存后变白了? 检查是否保存成了 JPEG,或被编辑软件铺上了底色。

图里的文字可以直接发布吗? 应逐字检查,尤其是中文笔画、数字、商标与长句。

API access

API documentation

gpt-image-2

Use the linked documentation for model-specific request parameters and examples.

Code samples

RequestPOST/v1/images/generations
Example request
Parameters
ParameterTypeDefault / rangeDescription
promptrequired
string—Text description of the desired image
size
enum
=1024x1024
Output image size
quality
enum
=standard
Generation quality preset
style
enum
=vivid
Aesthetic style
n
integer
=11 ~ 10
Number of images to generate
response_format
enum
=url
How to deliver the resulting image

Replace <YOUR_API_KEY> with the API key from your token settings.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Supported parameters

Generation parameters
ParameterTypeDefault / rangeDescription
promptrequired
string—Text description of the desired image
size
enum
=1024x1024
Output image size
quality
enum
=standard
Generation quality preset
style
enum
=vivid
Aesthetic style
n
integer
=11 ~ 10
Number of images to generate
response_format
enum
=url
How to deliver the resulting image

Rate limits

SupplierRPMTPMRPD
GPT官+AZ 混合UnlimitedUnlimitedUnlimited
OpenAIUnlimitedUnlimitedUnlimited
优质按次UnlimitedUnlimitedUnlimited
标准按次UnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about gpt-image-2

What is gpt-image-2?

Compare gpt-image-2 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call gpt-image-2?

Create an API key with access to gpt-image-2, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is gpt-image-2 priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate gpt-image-2 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.