SAM 3 RLE is a unified foundation model for promptable image segmentation using text, points, or boxes to detect and segment objects. Returns RLE (Run-Length Encoding) encoded masks for efficient storage and processing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle

$0.005per run·~200 / $1
the juice
the boat
the man
the woman
the cat
SAM3 Image Segmentation RLE is an advanced image segmentation model based on Meta's Segment Anything Model 3. It returns segmentation masks in RLE (Run-Length Encoding) format — a compact, program-friendly output ideal for API integration, automated pipelines, and machine learning workflows.
RLE output format Returns compact Run-Length Encoded mask data instead of image files — smaller payload, faster transfer.
Multiple prompt types Segment objects using text prompts, point prompts, box prompts, or any combination.
API-optimized Designed for programmatic use, batch processing, and automated workflows.
COCO-compatible RLE format is directly compatible with COCO dataset tools and annotation pipelines.
Prompt Enhancer Built-in tool to automatically improve your text prompts for better results.
Ultra-affordable Just $0.005 per image for professional-quality segmentation.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Source image to segment (upload or URL) |
| prompt | No* | Text description of the object to segment |
| point_prompts | No* | Point coordinates to identify the target object |
| box_prompts | No* | Bounding box coordinates to identify the target object |
| apply_mask | No | Overlay the segmentation mask on the original image |
*At least one prompt type (text, boxes, or points) must be provided.
The model returns RLE (Run-Length Encoding) data in JSON format:
{
"rle": "146301 3 147834 11 149368 14 150903 16..."
}
from pycocotools import mask as mask_utils
rle_data = {"counts": "146301 3 147834 11...", "size": [height, width]}
binary_mask = mask_utils.decode(rle_data) # Returns numpy array
| Item | Cost |
|---|---|
| Per image | $0.005 |
Simple flat-rate pricing regardless of image size or prompt complexity.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/sam3-image-rle with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Sam3 Image Rle below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"apply_mask": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/sam3-image-rle" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/sam3-image-rle";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"apply_mask": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"apply_mask": True
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/sam3-image-rle", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Sam3 Image Rle is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. SAM 3 RLE is a unified foundation model for promptable image segmentation using text, points, or boxes to detect and segment objects. Returns RLE (Run-Length Encoding) encoded masks for efficient storage and processing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/sam3-image-rle.
Sam3 Image Rle starts at $0.005 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `apply_mask`, `box_prompts`, `enable_sync_mode`, `point_prompts`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/sam3-image-rle.
Median end-to-end generation time on WaveSpeedAI is around 6 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.