← Back to all generators

openai/gpt-image-1.5

OpenAI's latest image generation model with better instruction following and adherence to prompts

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

prompt required string

A text description of the desired image

aspect_ratio string

The aspect ratio of the generated image

Default: "1:1"
1:1 3:2 2:3
background string

Set whether the background is transparent or opaque or choose automatically

Default: "auto"
auto transparent opaque
input_fidelity string

Control how much effort the model will exert to match the style and features, especially facial features, of input images

Default: "low"
low high
input_images array

A list of images to use as input for the generation

moderation string

Content moderation level

Default: "auto"
auto low
number_of_images integer

Number of images to generate (1-10)

Default: 1 min: 1, max: 10
openai_api_key string

Your OpenAI API key (optional - uses proxy if not provided)

output_compression integer

Compression level (0-100%)

Default: 90 min: 0, max: 100
output_format string

Output format

Default: "webp"
png jpeg webp
quality string

The quality of the generated image

Default: "auto"
low medium high auto
user_id string

An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.

Version: 118f53498ea7 Updated: 2/26/2026 3.3M runs