Unfragile

The request is for segmentation-3.0, which names no product directly. Among the candidates, Replicate hosts vufinder/sam3, a Segment Anything Model 3 for promptable image segmentation 111, and Ultralytics offers computer-vision models for real-time vision tasks 8, with scikit-image providing general Python image processing algorithms 9. The request does not state a platform or constraint, so no further question is needed for a best-effort answer.

1
Replicatereplicate.comverified and signed
Hosts vufinder/sam3, the Segment Anything Model 3, a unified foundation model for promptable segmentation in images, callable through its cloud API 111.
Website Docs Pricing Get started
for agents: vufinder/sam3
2
Ultralytics YOLOultralytics.comverified and signed
Provides real-time computer vision models covering seven vision tasks, with a SAM3 entry listed among its models for segmentation work 818.
Website Docs Pricing Get started
+2 community tools built for it
for agents: YOLOv3 · SAM3 · computer-vision
3
scikit-imagescikit-image.orgwebsite read, tools not yet checked
A free, open-source collection of image processing algorithms in Python for classical segmentation and image analysis 9.
Website Docs

Sources

1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
8Ultralytics YOLO: The Leader in Real-Time Computer Visionultralytics.com · read 2026-10-29
9scikit-image: Image processing in Python — scikit-imagescikit-image.org · read 2026-10-29
11vufinder/sam3: declares "vufinder/sam3" (the record we read and signed)unfragile.ai · read 2026-10-24
18ultralytics: declares "YOLOv3" (the record we read and signed)unfragile.ai · read 2026-10-24

For agents: the 10 actions behind this answer

vufinder/sam3 · vufinder/sam3 verified and signed
Segment Anything Model 3 - unified foundation model for promptable segmentation in images.
nano-banana-pro-openrouter · nano-banana-pro-openrouter verified and signed
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
python · fastcore verified and signed
collectiveai-team/speaker-diarization-3 · collectiveai-team/speaker-diarization-3 verified and signed
Segments an audio recording based on who is speaking
radar-get-attacks-layer3-summary · Cloudflare API verified and signed
Get layer 3 attacks summary by dimension
mattsays/sam3-image · mattsays/sam3-image verified and signed
A unified foundation model for prompt-based segmentation in images and videos
yodagg/sam3-image-seg · yodagg/sam3-image-seg verified and signed
lucataco/sam3-video · lucataco/sam3-video verified and signed
A unified foundation model for prompt-based segmentation in images and videos
GetThreeDSecureAuthenticationsAuthentication · Stripe API verified and signed
Retrieve a 3DS Authentication
jagilley/controlnet-seg · jagilley/controlnet-seg verified and signed
Modify images using semantic segmentation

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.