Meta modelsimage generation api

meta/sam-3-1/video

Name: Sam 3 1
Author: Meta

Sam 3 1 Video is Meta's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Input

Prompt(string)

Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').

Video Url(string)

The URL of the video to be segmented.

Box Prompts(array)

List of box prompt coordinates (x_min, y_min, x_max, y_max).

Point Prompts(array)

List of point prompts

Detection Threshold(number)

0.11

Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Range: 0.1 to 1.

Apply Mask(boolean)

Apply the mask on the video.

Video Output Type(string)

The output type of the generated video. Allowed values: X264 (.mp4), VP9 (.webm).

Max Num Objects(integer)

1128

Maximum number of objects to track in the video. Range: 1 to 128.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

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

Model IDmeta/sam-3-1/video

Input Schema

8 parameters · 1 required · 7 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth'). · Default: ""
`video`	string	Optional	The URL of the video to be segmented.
`apply_mask`	boolean	Optional	Apply the mask on the video. · Default: true
`box_prompts`	object[]	Optional	List of box prompt coordinates (x_min, y_min, x_max, y_max). · Default: []
`point_prompts`	object[]	Optional	List of point prompts · Default: []
`max_num_objects`	integer	Optional	Maximum number of objects to track in the video. · Min: 1 · Max: 128 · Default: 16
`video_output_type`	string	Optional	The output type of the generated video. · Options: X264 (.mp4), VP9 (.webm) · Default: "X264 (.mp4)" X264 (.mp4)VP9 (.webm)
`detection_threshold`	number	Optional	Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. · Min: 0.1 · Max: 1 · Default: 0.5

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "meta/sam-3-1/video",
  "video": "https://static.sandbase.ai/examples/meta/sam-3-1/video/input_video_0.mp4",
  "prompt": "person",
  "apply_mask": true,
  "box_prompts": [],
  "point_prompts": [],
  "max_num_objects": 16,
  "video_output_type": "X264 (.mp4)",
  "detection_threshold": 0.5
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Sam 3 1

API README

Sam 3 1 Video

Sam 3 1 Video is built for promptable segmentation and reconstruction, with this exact route focused on temporally tracked video segmentation. Sam 3 1 Video is Meta's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification. 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, sync_mode, video_url, apply_mask, box_prompts, point_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

Temporally Tracked Video Segmentation. The meta/sam-3-1/video route is dedicated to temporally tracked video segmentation, keeping inputs and outputs matched to this operation.
Precise Spatial Selection. Within meta/sam-3-1/video, documented prompt and media controls direct precise spatial selection while keeping the brief close to the result.
Structured Masks Or Geometry. The meta/sam-3-1/video result provides structured masks or geometry in a machine-consumable form for review and downstream production.
Route-specific control. For meta/sam-3-1/video, documented controls include prompt, sync_mode, video_url, apply_mask, box_prompts, point_prompts, defining the supported variation space for this exact route.

Pricing

Configuration	Price
Per request	`$0.010000`

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically temporally tracked video 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-3-1/video` 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": ""
}

Technical Specs

Property	Value
Model ID	`meta/sam-3-1/video`
Required inputs	`prompt`
`prompt`	string; default:
`sync_mode`	boolean; default: false
`video_url`	string
`apply_mask`	boolean; default: true
`box_prompts`	array; default: []
`point_prompts`	array; default: []
`max_num_objects`	integer; default: 16
`safety_tolerance`	string; default: 6
`video_output_type`	string; options: X264 (.mp4), VP9 (.webm); default: x264 (.mp4)
`detection_threshold`	number; default: 0.5

Related Models

meta/sam-3-1/image
meta/sam-3-1/image-rle
meta/sam-3-1/video-rle