SAM 2 (Segment Anything 2)
sam-2Meta Segment Anything 2. Promptable segmentation across images and video with temporal memory. Zero-shot, point/box/mask prompts, fast on a single H100.
- Price
- ≈ US$0.018/run
- Input → output
- Text + Image + Video → Text
- Developer
- Meta
- Updated
- September 23, 2026
Playground
Try SAM 2 (Segment Anything 2)
No input form
No input form for this model yet
Its inputs are not documented yet. So that no run fails on a wrong input, we don't offer a form here. Pick a comparable model instead.
Examples
Open full size
InputNo text prompt: the model only takes the input shown.
Open full size
InputNo text prompt: the model only takes the input shown.
About SAM 2 (Segment Anything 2)
SAM 2 (Segment Anything 2) is a model by Meta in the Multimodal category. On Railwail, SAM 2 (Segment Anything 2) costs ≈ US$0.018 per run.
Pricing
| Typical run (≈ 15 s on L40S) | US$0.018 per run |
|---|---|
| GPU time (L40S) | US$0.00117 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = US$0.01
Cost calculator
Price calculator
Typical according to the provider: about 15.4 s
Total
US$1.80
180 credits
Per run
US$0.018 · 1.8 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
sam-2- Developer
- Meta
- Category
- Multimodal
- Input
- Text, Image, Video
- Output
- Text
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- September 23, 2026
Tags
- replicate
- segmentation
- meta
- vision-understanding
- open-weights
Frequently asked questions
What is SAM 2 (Segment Anything 2)?
SAM 2 (Segment Anything 2) is a model by Meta in the Multimodal category.
How much does SAM 2 (Segment Anything 2) cost on Railwail?
On Railwail, SAM 2 (Segment Anything 2) costs ≈ US$0.018 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
How fast is SAM 2 (Segment Anything 2)?
There are not enough measured runs of SAM 2 (Segment Anything 2) on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is SAM 2 (Segment Anything 2) better than BLIP?
That depends on the task. SAM 2 (Segment Anything 2) (Meta) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.
Compare SAM 2 (Segment Anything 2) and BLIPCan SAM 2 (Segment Anything 2) process images?
Yes. SAM 2 (Segment Anything 2) accepts images as input in addition to text.
Comparable models
All in this category- BLIPSalesforce
Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.
- CLIP InterrogatorCommunity
pharmapsychotic's CLIP Interrogator. Takes an image and produces a Stable-Diffusion-style text prompt by combining BLIP captioning with CLIP to rank likely subjects, artists, mediums and styles. Commonly used to reverse-engineer a prompt from an existing picture.
≈ US$0.0457/run
154 % more expensive per unit
Compare SAM 2 (Segment Anything 2) vs. CLIP Interrogator - Depth Anything v2Community
Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.