Sam3 Image API Documentation

Sam3 Image API Documentation

Playground

SAM 3 is a unified foundation model for promptable image segmentation using text, points, or boxes to detect and segment objects. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

SAM3 Image Segmentation segments target objects in an image using flexible prompt inputs. Provide an image and use a text prompt, point prompts, box prompts, or a combination of them to generate a precise segmentation result for the selected subject.

Why Choose This?

• Image segmentation workflow
  Segment people, objects, animals, backgrounds, or other visible targets from a source image.

• Multiple prompt types
  Use text prompts, point prompts, box prompts, or combined prompt guidance for more accurate targeting.

• Text-based target selection
  Describe what to segment with natural language, such as the man, the car, or background.

• Point and box control
  Use coordinates or bounding boxes when you need more precise target selection.

• Mask output control
  Use apply_mask to choose whether the mask is applied to the image or returned as a black-and-white mask-style output.

• Low-cost segmentation
  Generate segmentation outputs at a fixed price per image.

Parameters

At least one prompt type must be provided: prompt, point_prompts, or box_prompts.

How to Use

1. Upload an image — Provide the source image you want to segment.
2. Add a target prompt — Use a text prompt, point prompts, box prompts, or a combination of them.
3. Choose mask behavior — Enable apply_mask to apply the mask to the image. Disable it when you need a black-and-white mask output.
4. Choose output format — Select jpeg, png, or webp.
5. Submit — Generate the segmentation result.

Pricing

Pricing is fixed at $0.005 per image.

Image size, prompt type, apply_mask, and output_format do not add separate charges.

Best Use Cases

• Object segmentation — Segment people, products, animals, vehicles, clothing, or props.
• Background workflows — Target foreground subjects or background regions for downstream editing.
• Mask generation — Create black-and-white mask-style outputs for compositing or image editing.
• Object isolation — Isolate selected objects for design, marketing, or post-production workflows.
• Data annotation — Generate segmentation masks for dataset preparation or labeling workflows.
• E-commerce assets — Segment products for catalog images, ads, and layout workflows.

Pro Tips

• Use short, concrete text prompts such as person, dog, car, or background.
• Use point prompts when text alone is ambiguous.
• Use box prompts when you need to constrain segmentation to a specific region.
• Combine text, points, and boxes when the target is difficult to isolate.
• Use apply_mask=true when you want the mask applied to the original image.
• Use apply_mask=false when you need a black-background mask output with the selected region shown in white.
• Use png when working with mask or compositing workflows.

Notes

• image is required.
• At least one of prompt, point_prompts, or box_prompts must be provided.
• Point and box prompts use image coordinates.
• When apply_mask is disabled, the output is a mask-style image with a black background and the selected region in white.
• output_format defaults to png.

Related Models

• Bria RMBG — Remove image backgrounds for subject isolation workflows.
• Qwen Image Edit 2511 — Edit images with text instructions.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "apply_mask": true,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/sam3-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters