gpt-image-2 API

Use the exact model ID gpt-image-2. The model field must match this page exactly.

Sample outputgpt-image-2POST /v1/images/generations

Parameters: size=1536x1024n=1

Prompt: A 24-hour laundromat at three in the morning, a whole wall of front-loaders turning. A young man in a silver metallic bomber jacket has just tipped a jar of coloured glass marbles into the nearest drum. The marbles are pouring upward out of the open door instead of sinking, already arcing across the room in a bright teal and amber bridge that rings against the ceiling lights. Cold cyan tubes overhead, a hard warm amber glow thrown out of the drum itself. Straight-on symmetrical camera, wide, hyper-real detail in the glass, film grain, no text.

Request that produced this sample

{
  "model": "gpt-image-2",
  "prompt": "A 24-hour laundromat at three in the morning, a whole wall of front-loaders turning. A young man in a silver metallic bomber jacket has just tipped a jar of coloured glass marbles into the nearest drum. The marbles are pouring upward out of the open door instead of sinking, already arcing across the room in a bright teal and amber bridge that rings against the ceiling lights. Cold cyan tubes overhead, a hard warm amber glow thrown out of the drum itself. Straight-on symmetrical camera, wide, hyper-real detail in the glass, film grain, no text.",
  "n": 1,
  "size": "1536x1024"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/images/generations.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Generate an image

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A white cat runs through a neon-lit street in the rain",
    "size": "1024x1024", "n": 1
  }'

Request notes

OpenAI-compatible image models use prompt, n, size, and quality; use editing only when the official page documents it.

Request parameters

GPT Image uses the OpenAI-compatible Images API. Generation uses JSON; editing and mask-guided editing use multipart. GPT Image 2 returns Base64 image data in data[].b64_json.

Field	Required	Notes
model	Yes	gpt-image-2
prompt	Yes	Generation or editing instruction
size	No	auto or custom WIDTHxHEIGHT within the documented size rules
quality	No	low / medium / high / auto; default auto
background	No	auto / opaque / transparent; transparent backgrounds require PNG or WebP output
output_format	No	png / jpeg / webp
output_compression	No	0–100 for JPEG/WebP, default 100; ignored for PNG
moderation	No	auto / low; default auto
n	No	1–10 outputs; default 1

Response and input limits

Custom sizes require both edges to be multiples of 16, a 1:3 to 3:1 aspect ratio, a maximum edge of 3,840 pixels, and 655,360–8,294,400 total pixels. Editing accepts up to 16 source images, each source and mask under 50 MB; do not send DALL·E-only response_format.

Edit images

GPT Image 2 edits use /v1/images/edits with multipart image/image[]; up to 16 input images are accepted, and the mask must match the first image’s format and dimensions.

bash

curl https://modelflare.dev/v1/images/edits \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -F "model=gpt-image-2" \
  -F "image[]=@/path/to/product.png" \
  -F "mask=@/path/to/mask.png" \
  -F "prompt=保持主体不变，将背景替换为暖色摄影棚渐变" \
  -F "size=1536x1024" \
  -F "quality=high" \
  -F "output_format=png" \
  -F "n=1"

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID; use the response fields and error message defined by the selected model contract.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses token-based billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.