Loading page…
The hosted model combines detection, pixel-level masks and identity-preserving video tracks in one request, aiming to remove the need to assemble and tune separate vision systems.
Listen to this story
Meta is making SAM 3.1 available as a hosted service through the Meta Model API, letting developers use one zero-shot model for text-prompted object detection, pixel-level segmentation and video tracking. The API is priced at $2.50 per 1,000 images and $0.20 per 1,000 video frames, with a playground, documentation and OpenAI SDK-compatible access.
SAM 3.1 returns bounding boxes, segmentation masks and persistent video tracks for prompted objects.
Pricing is $2.50 per 1,000 images and $0.20 per 1,000 video frames.
Meta says developers need no training data or fine-tuning, and can test media in a playground.
Meta has released SAM 3.1 through its Meta Model API, giving developers hosted access to a vision model that can identify objects, draw pixel-level boundaries around them and follow them through video. The release packages tasks often handled as separate outputs into one request, with Meta positioning it as a zero-shot system that needs no training data or fine-tuning.
The launch makes the model available as a self-serve service. Meta offers API access, documentation and a playground for testing media before code is written. It also says developers can point existing OpenAI SDK-compatible clients at the Meta Model API, which could make the service easier to adopt for teams already using those clients.
SAM 3.1 is designed to detect objects in images and video, return a bounding box and a segmentation mask for each match, then track objects over time while preserving their identities. A segmentation mask marks the exact pixels belonging to an object, rather than only drawing a rectangular box around it. Meta says a developer can name an object with a short text prompt and receive those results without adding separate models.
Meta lists SAM 3.1 image segmentation at $2.50 per 1,000 images.
Meta lists video use at $0.20 per 1,000 frames.
Meta says SAM 3.1 runs on inference infrastructure purpose-built for the model’s DETR architecture, and promotes production throughput without customers needing to host or tune the model themselves. Those performance and deployment claims come from Meta, but they clarify the product’s target: teams that want a ready-made vision capability rather than a model to operate.
The next question is whether the zero-shot approach holds on the media and object categories a developer actually needs to handle. Meta has published access routes and per-image and per-frame rates, but reliable results on particular imagery and video will still determine how useful the service is in production.
Editorial analysis
Meta is turning a specialized perception workflow into another building block inside Meta Model API. SAM 3.1’s pitch is operational as much as technical: developers can request detection, exact object outlines and video tracking through one hosted service rather than assemble separate components. That fits Meta’s wider effort to offer several model types through a common API surface. The meaningful next test is whether developers find the zero-shot results dependable on their own media, especially when tracking identities across video. Meta’s listed image and frame rates make that assessment easier to price, but not easier to validate.
Loading discussion...
Join the conversation
Explain what testing would earn your confidence.
Be the first to share a perspective or an experience.
Reader comments
Newest comments first. Replies stay oldest first.