ReplicateImage to imageComing soon

openai/gpt-image-1.5

Name: openai/gpt-image-1.5
Brand: Replicate

openai/gpt-image-1.5 is an image to image tool from Replicate that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

quality: low $0.0169, medium $0.065, auto (default) $0.1768, high $0.1768 per image. Billed on number_of_images, default 1.

Limits

Runs: In the background
Returns: image
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	A text description of the desired image
`quality`	JSON	auto	The quality of the generated image
`user_id`	text	—	An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.
`background`	JSON	auto	Set whether the background is transparent or opaque or choose automatically
`moderation`	JSON	auto	Content moderation level
`aspect_ratio`	JSON	1:1	The aspect ratio of the generated image
`input_images`	list	—	A list of images to use as input for the generation
`output_format`	JSON	webp	Output format
`input_fidelity`	JSON	low	Control how much effort the model will exert to match the style and features, especially facial features, of input images
`openai_api_key`	text	—	Your OpenAI API key (optional - uses proxy if not provided)
`number_of_images`	number (whole) 1 to 10	1	Number of images to generate (1-10)
`output_compression`	number (whole) 0 to 100	90	Compression level (0-100%)

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "openai/gpt-image-1.5",
    "input": {
      "prompt": "<prompt>"
    }
  }'