maskstring
The URL of the mask image to use for the generation. This indicates what part of the image to edit.
openai/gpt-image-1.5/editGpt Image 1.5 Edit by OpenAI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.
Try the model
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Select an example to load its inputs and result into the playground.
{
"prompt": "Same workers, same beam, same lunch boxes - but they're all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new priorities. A hard hat has AirPods."
}Human preference
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
GPT Image 1.5 edit: change images with an instruction, with an optional mask for local edits and input_fidelity to keep faces and logos close to the original.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 32,000 characters. |
images | image URL[] | — | Images to edit, Image 1, Image 2, … |
mask | image URL | — | Optional PNG mask; transparent areas are edited. |
aspect_ratio | 1:1 / 2:3 / 3:2 | — | 1:1, 3:2, or 2:3; non-square sizes cost more. |
output_format | jpeg / png | png | Output file format. |
input_fidelity | low / high | high | high preserves faces and logos more closely. |
quality | low / medium / high | high | Higher quality costs more; high is the default. |
background | auto / transparent / opaque | auto | transparent returns a PNG with alpha. |
Price depends on quality and shape, per output image:
| Quality | 1:1 | 3:2 or 2:3 |
|---|---|---|
| low | $0.009 | $0.013 |
| medium | $0.034 | $0.051 |
| high | $0.133 | $0.20 |
Failed runs are not charged.
Related: openai/gpt-image-1.5, openai/gpt-image-2/edit (newer).
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "openai/gpt-image-1.5/edit",
"images": [
"https://static.sandbase.ai/examples/openai/gpt-image-1.5/edit/input_images_0.png"
],
"prompt": "Same workers, same beam, same lunch boxes - but they're all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new priorities. A hard hat has AirPods.",
"quality": "high",
"background": "auto",
"output_format": "png",
"input_fidelity": "high"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
maskstringThe URL of the mask image to use for the generation. This indicates what part of the image to edit.
imagesarrayThe URLs of the images to use as a reference for the generation.
promptstringrequiredThe prompt for image generation
qualitystringQuality for the generated image
Default: "high"
Possible values: "low", "medium", "high"
backgroundstringBackground for the generated image
Default: "auto"
Possible values: "auto", "transparent", "opaque"
aspect_ratiostringThe aspect ratio of the generated image.
Possible values: "1:1", "2:3", "3:2"
output_formatstringOutput format for the images
Default: "png"
Possible values: "jpeg", "png"
input_fidelitystringInput fidelity for the generated image
Default: "high"
Possible values: "low", "high"
{
"model": "openai/gpt-image-1.5/edit",
"images": [
"https://static.sandbase.ai/examples/openai/gpt-image-1.5/edit/input_images_0.png"
],
"prompt": "Same workers, same beam, same lunch boxes - but they're all on their phones now. One is taking a selfie. One is on a call looking annoyed. Same danger, new priorities. A hard hat has AirPods.",
"quality": "high",
"background": "auto",
"output_format": "png",
"input_fidelity": "high"
}A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "OpenAI Platform",
"source_url": "https://platform.openai.com/docs/guides/image-generation",
"url": "https://static.sandbase.ai/examples/67f8ab24-ea67-4e98-8a05-46c1be76bc02/output/a561e4d6-c6b8-4ed8-b909-e12983309b9d.png"
}
]