SAM 3 Image
Image editing
Starting price $0.01 / request
Moondream 2 finds a thing you name in a photo and shows where it is, as a box or as a point.
moondream2/point-object-detectionThis model has other modes with their own ids: moondream2/object-detection.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moondream2/point-object-detection",
"input": {
"image_url": "https://example.com/input.png",
"object": "the person'\''s left hand"
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "moondream2/point-object-detection", "quote_id": "QUOTE_ID", "input": {"image_url":"https://example.com/input.png","object":"the person'\''s left hand"}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
image_urlrequired | string (image URL) | URL of the image to be processed |
objectrequired | string | Object to be detected in the image |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Upload an image and type the object to look for, such as "red car", "coffee cup" or "person wearing a hat". Object detection marks each match with a box around it; point detection marks the center of each match with a single point.
Check missed objects and incorrect detections manually; detection is not a segmentation cutout.