Sam 3

Name: Meta Sam 3
Price: 0.005 USD
Availability: InStock
Author: Meta

meta/sam-3/image-rle

Sam 3 Image Rle is Meta's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Use in agent Get API key

Base price: $0.005USD / run
Execution: async
Model type: image
Input fields: 11

Try the model

Playground

Open playground

Input

Prompt(string)

Text prompt for segmentation

Image Url(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be segmented

This field is required.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Apply Mask(boolean)

Apply the mask on the image.

Max Masks(integer)

132

Maximum number of masks to return when `return_multiple_masks` is enabled. Range: 1 to 32.

Include Scores(boolean)

Whether to include mask confidence scores.

Box Prompts(array)

Box prompt coordinates (x_min, y_min, x_max, y_max). Multiple boxes supported - use object_id to group boxes for the same object or leave empty for separate objects.

Return Multiple Masks(boolean)

If True, upload and return multiple generated masks as defined by `max_masks`.

Text Prompt(string)

[DEPRECATED] Use 'prompt' instead. Kept for backward compatibility.

Point Prompts(array)

List of point prompts

Include Boxes(boolean)

Whether to include bounding boxes for each mask (when available).

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Model card

Specifications

Pricing

Base price: $0.005 / run

Context & modalities

Input: Schema-defined
Output: image

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Meta
Model ID: meta/sam-3/image-rle
Execution: async
Base URL: https://api.sandbase.ai
API: Unified Run API
Endpoint: /v1/run

API README

Sam 3 Image Rle

Sam 3 Image Rle is built for promptable segmentation and reconstruction, with this exact route focused on run-length encoded image segmentation. Sam 3 Image Rle is Meta's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion. It is designed for production workflows that need a clearly scoped media operation instead of a generic assistant response, preserving the supplied direction while returning an artifact ready for review, iteration, or downstream assembly.

The request surface keeps creative direction and delivery choices explicit through prompt, image_url, max_masks, sync_mode, apply_mask, box_prompts. Teams can lock source material, describe the intended result, choose supported output controls, and rerun the same request structure across variations. This makes experiments easier to compare and larger pipelines easier to operate without hiding important decisions inside an opaque preset.

Highlights

Run-Length Encoded Image Segmentation. The meta/sam-3/image-rle route is dedicated to run-length encoded image segmentation, keeping inputs and outputs matched to this operation.
Precise Spatial Selection. Within meta/sam-3/image-rle, documented prompt and media controls direct precise spatial selection while keeping the brief close to the result.
Structured Masks Or Geometry. The meta/sam-3/image-rle result provides structured masks or geometry in a machine-consumable form for review and downstream production.
Route-specific control. For meta/sam-3/image-rle, documented controls include prompt, image_url, max_masks, sync_mode, apply_mask, box_prompts, defining the supported variation space for this exact route.

Pricing

Configuration	Price
Per request	`$0.005000`

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically run-length encoded image segmentation, not a neighboring generation or editing task.
Production iteration	When creative teams need repeatable precise spatial selection with an explicit request payload.
Automated pipelines	When structured masks or geometry must flow into review, storage, compositing, or publishing.
Controlled variations	When a stable brief should be rerun while changing only documented inputs.
Prototype to scale	When the same `meta/sam-3/image-rle` contract should serve a single experiment and a larger batch later.

Prompt Guide

Lead with the subject or source, then state the transformation, important spatial or temporal details, style, and finish. Supply only documented fields, keep media URLs reachable, and vary one control at a time when comparing outputs.

{
  "prompt": "wheel",
  "image": "https://example.com/reference.jpg"
}

Technical Specs

Property	Value
Model ID	`meta/sam-3/image-rle`
Required inputs	`prompt`
`prompt`	string; default: wheel
`image_url`	string
`max_masks`	integer; default: 3
`sync_mode`	boolean; default: false
`apply_mask`	boolean; default: true
`box_prompts`	array; default: []
`text_prompt`	string
`include_boxes`	boolean; default: false
`output_format`	string; options: jpeg, png, webp; default: png
`point_prompts`	array; default: []
`include_scores`	boolean; default: false
`safety_tolerance`	string; default: 6
`return_multiple_masks`	boolean; default: false

Related Models

meta/sam-3/3d-align
meta/sam-3/3d-body
meta/sam-3/3d-objects
meta/sam-3/image

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

meta/sam-3/image-rle

# 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 $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "meta/sam-3/image-rle",
  "image": "https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg",
  "prompt": "wheel",
  "max_masks": 3,
  "apply_mask": true,
  "box_prompts": [],
  "include_boxes": false,
  "output_format": "png",
  "point_prompts": [],
  "include_scores": false,
  "return_multiple_masks": false
}
SANDBASE_JSON
)
run_id=$(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"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
Sam 3This model `Meta`	Image	$0.01 / run	Nov 20, 2025
SAM 3 3D Objects `Meta`	Image	$0.02 / run	Dec 2, 2025
SAM 3 Image `Meta`	Image	$0.01 / run	Nov 20, 2025

Questions

FAQ

How do I call Meta Sam 3 through SandBase?

Create a SandBase API key, then send requests with the model ID "meta/sam-3/image-rle" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate Meta account?

No. One SandBase API key and balance gives you access to Meta Sam 3 and the other models in the catalog; you do not need to sign up with Meta separately.