GPT Image

Parameters below were verified against the live model directory on November 5, 2026. Check the model directory for current schema, availability, and prices.

Overview

GPT Image 2 is OpenAI’s advanced model for high-quality image generation and editing. It is designed for production workflows that require detailed instruction following, readable text, complex compositions, photorealistic detail, and controlled changes to existing images. GPT Image 2 creates new visuals from natural-language prompts and edits existing assets through the same model. It can replace backgrounds, add or remove objects, adjust visual details, and build new compositions from references. This unified workflow reduces the need to switch between separate generation and editing tools.

The full model guide, live parameter schema, and playground for every model ID are available in the HiPix model directory.

Model IDs

Model ID	Mode	Notes
`openai/gpt-image-2`	Image-to-Image, Text-to-Image
`openai/gpt-image-2-5-flare-economy`	Image-to-Image, Text-to-Image
`openai/gpt-image-2-5-sunburst-economy`	Image-to-Image, Text-to-Image
`openai/gpt-image-2-economy`	Image-to-Image, Text-to-Image
`openai/gpt-image-2/text-to-image`	Text-to-Image

Parameters

Requests are submitted to POST /v1/videos (video) or POST /v1/images/generations / POST /v1/images/edits (image). Fields marked metadata.* travel inside the metadata object.

`openai/gpt-image-2`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`image`	array	No	up to 10; ≤10 MB each; images
`size`	enum	Yes	`1024x1024`, `1152x864`, `864x1152`, `1664x2496`, `2496x1664`, `2048x2048`, `2560x1440`, `1440x2560`, `3840x2160`, `2160x3840`; default `1024x1024`
`quality`	enum	Yes	`low`, `medium`, `high`; default `medium`
`format`	enum	Yes	`png`, `jpeg`; default `png`

`openai/gpt-image-2-5-flare-economy`, `openai/gpt-image-2-5-sunburst-economy`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`image`	array	No	up to 16; ≤20 MB each; images
`size`	enum	Yes	`1024x1024`, `1152x864`, `864x1152`, `1664x2496`, `2496x1664`, `2048x2048`, `2560x1440`, `1440x2560`, `3840x2160`, `2160x3840`; default `2560x1440`
`quality`	enum	Yes	`low`, `medium`, `high`; default `medium`
`format`	enum	Yes	`png`, `jpeg`; default `png`

`openai/gpt-image-2-economy`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`image`	array	No	up to 16; ≤10 MB each; images
`size`	enum	Yes	`1024x1024`, `1152x864`, `864x1152`, `1664x2496`, `2496x1664`, `2048x2048`, `2560x1440`, `1440x2560`, `3840x2160`, `2160x3840`; default `1440x2560`
`quality`	enum	Yes	`low`, `medium`, `high`; default `medium`
`format`	enum	Yes	`png`, `jpeg`; default `png`

`openai/gpt-image-2/text-to-image`

API field	Type	Required	Values / limit
`prompt`	string	Yes	—
`size`	enum	Yes	`1024x1024`, `1152x864`, `864x1152`, `1664x2496`, `2496x1664`, `2048x2048`, `2560x1440`, `1440x2560`, `3840x2160`, `2160x3840`; default `864x1152`
`quality`	enum	Yes	`low`, `medium`, `high`; default `medium`
`format`	enum	Yes	`png`, `jpeg`; default `png`

Example

A minimal request for openai/gpt-image-2/text-to-image:

curl -X POST https://api.apimart.cc/v1/images/generations \
  -H "Authorization: Bearer $HIPIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-image-2/text-to-image", "prompt": "A kitten running through a sunlit garden", "size": "864x1152", "quality": "medium", "format": "png"}'

Limits, availability, and pricing

Submit only the input types listed for the exact model ID; unsupported inputs are rejected or removed on HiPix.
See Submit a Video Task or the model directory for the full request contract, and Pricing & Billing for how charges are settled.
Prices and availability are shown per model ID in the model directory.