gpt-image-2

Name: gpt-image-2
Brand: OpenAI
Price: 3.75 USD
Availability: InStock

Image

Flexible sizing and high-fidelity reference inputs; faster generation and editing; stronger multilingual text and complex layouts.

Input price

$3.7525% off

Market: $5

/ M

Cache read

$0.937525% off

Market: $1.25

/ M

Image input

$625% off

Market: $8

/ M

Image output

$22.525% off

Market: $30

/ M

Image cache read

$1.525% off

Market: $2

/ M

Input

Text

Output

Image

Input

Prompt *

Size

生成图像尺寸，gpt-image-2 支持任意 WIDTHxHEIGHT（边长需被 16 整除，宽高比 1:3 到 3:1）。

Count 1

110

生成图像的数量，取值 1 到 10 之间。

Quality

生成图像的质量档，GPT 图像模型支持 low、medium、high，auto 自动选择。

Background

生成图像的背景，gpt-image-2 的透明背景支持处于预览阶段，用 transparent 时需输出 png 或 webp。

Output format

生成图像返回的编码格式，支持 png、jpeg 或 webp。

Output compression 100

0100

生成图像的压缩级别（0-100%），仅配合 webp 或 jpeg 输出格式时生效。

Moderation

GPT 图像模型的内容审核强度，low 为较宽松过滤，auto 为默认。

Output

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use openai/gpt-image-2 with the EasyAPI API:

Image models use the image generation endpoint. See image generation docs

cURL

curl https://token.easyapi.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{
  "model": "openai/gpt-image-2",
  "prompt": "A cute baby sea otter",
  "n": 1,
  "size": "auto",
  "quality": "auto",
  "background": "auto",
  "moderation": "auto",
  "output_compression": 100
}'

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl

curl -N https://token.easyapi.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"openai/gpt-image-2","prompt":"A cute baby sea otter","n":1,"size":"auto","quality":"auto","background":"auto","moderation":"auto","output_compression":100,"stream":true}'

Endpoint

Generates images from a text prompt.

POSThttps://token.easyapi.com/v1/images/generations

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: openai/gpt-image-2

Generate images from a prompt. The response includes data (url / b64_json) and usage fields. Docs

Parameters

Name	Type	Required	Default	Description
`model`	string	Yes	—	Image model ID, e.g. openai/gpt-image-1, qwen/qwen-image-2.0-pro or bytedance/seedream-4.0. Currently openai/gpt-image-2. Returns 400 model is required if missing
`prompt`	string	Yes	—	所需生成图像的文本描述，GPT 图像模型最大长度 32000 字符。；最大长度：32000
`background`	string	No	auto	生成图像的背景，gpt-image-2 的透明背景支持处于预览阶段，用 transparent 时需输出 png 或 webp。；可选：transparent / opaque / auto
`moderation`	string	No	auto	GPT 图像模型的内容审核强度，low 为较宽松过滤，auto 为默认。；可选：low / auto
`n`	integer	No	—	生成图像的数量，取值 1 到 10 之间。；范围：1 ~ 10
`output_compression`	integer	No	100	生成图像的压缩级别（0-100%），仅配合 webp 或 jpeg 输出格式时生效。；范围：0 ~ 100
`output_format`	string	No	—	生成图像返回的编码格式，支持 png、jpeg 或 webp。；可选：png / jpeg / webp
`partial_images`	integer	No	—	流式响应中生成的中间图像数量，取值 0 到 3，为 0 时一次性返回单张图。；范围：0 ~ 3
`quality`	string	No	auto	生成图像的质量档，GPT 图像模型支持 low、medium、high，auto 自动选择。；可选：low / medium / high / auto
`size`	string	No	—	生成图像尺寸，gpt-image-2 支持任意 WIDTHxHEIGHT（边长需被 16 整除，宽高比 1:3 到 3:1）。；可选：auto / 1024x1024 / 1536x1024 / 1024x1536
`stream`	boolean	No	false	是否以流式模式生成图像，仅 GPT 图像模型支持，默认为 false。

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

Related models

chatgpt-image-latest

OpenAI

Offering state-of-the-art visual quality, precise instruction following, and support for large-scale batch processing.

Image

15% off

Input price

$4.25/ M

Output price

$27.2/ M

Cache read

$1.0625/ M

Cache write

—

gpt-4.1

OpenAI

Stable code generation with predictable output.

TextMultimodal

15% off

Input price

$1.7/ M

Output price

$6.8/ M

Cache read

$0.425/ M

Cache write

$0/ M

gpt-4.1-mini

OpenAI

Near GPT-4o performance at lower latency and cost, suited for high-frequency interactions, coding, and vision tasks.

TextMultimodal

15% off

Input price

$0.34/ M

Output price

$1.36/ M

Cache read

$0.085/ M

Cache write

$0/ M

gpt-4.1-nano

OpenAI

Fastest GPT. Sub-second responses.

TextMultimodal

15% off

Input price

$0.085/ M

Output price

$0.34/ M

Cache read

$0.0213/ M

Cache write

$0/ M