imagestringrequired
The URL of the image to edit. Provide one http(s) or data: URL.
Default: ""
microsoft/mai-image-2.5-pro/editMai Image 2.5 Pro Edit by Microsoft - 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
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Customize your input with more control.
Your output will appear here
Complete the inputs, then click Run.
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.
MAI Image 2.5 Pro edit: Microsoft's top image model for photoreal edits from an instruction.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
image | image URL, required | — | Image to edit. JPEG, PNG, or WebP URL. |
output_format | jpeg / png | png | Output file format. |
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 | — | Output shape. |
$0.29 per output image.
| Request | Price |
|---|---|
| One image | $0.29 |
Failed runs are not charged.
Related: microsoft/mai-image-2.5/edit.
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "microsoft/mai-image-2.5-pro/edit",
"image": "https://storage.googleapis.com/falserverless/example_inputs/nano-banana-edit-input.png",
"prompt": "Turn this into a clean, futuristic product shot with soft studio lighting.",
"output_format": "png"
}
SANDBASE_JSON
)
run_id=$(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.
imagestringrequiredThe URL of the image to edit. Provide one http(s) or data: URL.
Default: ""
promptstringrequiredThe instruction describing how to edit the input image(s).
aspect_ratiostringThe aspect ratio of the generated image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
output_formatstringThe format of the generated image.
Default: "png"
Possible values: "jpeg", "png"
{
"model": "microsoft/mai-image-2.5-pro/edit",
"image": "https://storage.googleapis.com/falserverless/example_inputs/nano-banana-edit-input.png",
"prompt": "Turn this into a clean, futuristic product shot with soft studio lighting.",
"output_format": "png"
}A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.