Loading video route evidence
Reading current source runs and native formulas.
Reading current source runs and native formulas.
Provider source claims
ComputeLlama-owned measurements
Cataloged but never probed. No V4 observation is being presented as provider evidence.
Native source formulas
No complete native formula quote for this scenario.
No ComputeLlama callability observation.
Scenario decision trace
Append-only record
fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"metadata": {
"catalogDate": "2025-11-20T20:18:27.813Z",
"catalogStatus": "active"
},
"validFrom": null,
"releasedAt": null,
"validUntil": null,
"constraints": [],
"availability": "available",
"releaseVersion": null,
"availabilityRegions": []
}fal public video model catalog · stale at read time · 2.0.1 (succeeded)
{
"support": "supported",
"metadata": {
"tags": [
"segmentation",
"mask",
"real-time",
"rle"
],
"updatedAt": "2026-04-21T17:54:24.024Z",
"catalogDate": "2025-11-20T20:18:27.813Z",
"description": "SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ",
"licenseType": "commercial",
"catalogStatus": "active",
"catalogCategory": "video-to-video",
"openApiExpanded": true,
"openApiRouteCount": 3,
"catalogListedCategory": "video-to-video"
},
"asyncMode": "asynchronous",
"validFrom": null,
"confidence": "1.0000",
"validUntil": null,
"constraints": [],
"inputModalities": [
"image",
"text",
"video"
],
"outputModalities": [
"video"
]
}