Segment Anything 3.1
Segment Anything 3.1 is Meta's language model. A vision segmentation model that identifies and isolates objects within images and video with pixel-level precision.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard |
|---|---|
| Image In $ / image | |
| $0.0025 |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Segment Anything 3.1 | — | — | — | — | Current |
| SAM 3 | — | — | — | — | Available |
| SAM 2.1 Hiera Base Plus | — | — | — | — | Available |
| SAM 2.1 Hiera Large | — | — | — | — | Available |
| SAM 2.1 Hiera Small | — | — | — | — | Available |
| SAM 2.1 Hiera Tiny | — | — | — | — | Available |
| Segment Anything | — | — | — | — | Available |