@luxonis

Giving machines human-like vision. Edge AI cameras and open software that make Physical AI simple. Building the vision for a better future

 Denver, CO
luxonis.com
Joined December 2012
  • Tweets2.8K
  • Following216
  • Followers3.6K
687Media
Introducing OAK 4 FFC, the first OAK Modular device built on OAK 4. Your cameras, wherever the robot needs to see. One board for depth and AI.
6
14
7
139
114,519
Luxonis | Robotic Vision retweeted
Robert Scoble
@Scobleizer7h
This is next level for hardware! Robots don't always have room for a camera built for someone else's machine. @luxonis just launched OAK 4 FFC, the first OAK Modular board on OAK 4. You pick up to five cameras and put them wherever the robot needs to see. One board, 70 by 53 mm, runs the sync, calibration, stereo depth, and AI at 52 TOPS. You enter where the cameras sit in OAK Viewer. Dynamic Calibration then refines it from the scene, no printed target. Every camera captures at the same instant, so panorama and bird's eye stitching run on the board. It can be the robot's main computer or its dedicated vision system. Built for humanoids, drones, and other machines where a standard camera doesn't fit. Developer Kit is $849. Orders open today, shipping in November. luxonis.com/oak4-ffc
🤝 Paid partnership
19
9
76
6,841
Don't forget to enter into our giveaway with @OpenRoboticsOrg to win a free OAK 4 FFC! xitter.cf/luxonis/status/2115115…
Luxonis | Robotic Vision
@luxonis5h
We are giving away a free OAK 4 FFC! Comment on the @OpenRoboticsOrg community thread what your use case would be and our team will be hand picking the winner. Submissions close November 3rd, best of luck!
1
71
We are giving away a free OAK 4 FFC! Comment on the @OpenRoboticsOrg community thread what your use case would be and our team will be hand picking the winner. Submissions close November 3rd, best of luck!
Open Robotics@OpenRoboticsOrg5h
Win a OAK 4 FFC board-level vision computer from our new Silver OSRA member @Luxonis! To celebrate their membership and the simultaneous release of the OAK 4 FFC, Luxonis is giving away a dev kit to a community member: discourse.openrobotics.org/t…
An image of the OAK 4 FFC. The text on the image reads: ONE BOARD, NOT A STACK A custom multi-camera robot usually takes five vendors and months of glue code. Here it is one board. The usual rig: Compute module and carrier Capture card or deserializer Cameras from another vendor Drivers you maintain Your own sync and calibration OAK 4 FFC RVC4, 52 TOPS on board Five direct MIPI ports Calibrated camera modules DepthAI and Luxonis OS Synced, self-calibrating

ALT An image of the OAK 4 FFC. The text on the image reads: ONE BOARD, NOT A STACK A custom multi-camera robot usually takes five vendors and months of glue code. Here it is one board. The usual rig: Compute module and carrier Capture card or deserializer Cameras from another vendor Drivers you maintain Your own sync and calibration OAK 4 FFC RVC4, 52 TOPS on board Five direct MIPI ports Calibrated camera modules DepthAI and Luxonis OS Synced, self-calibrating

2
1
3
316
For more information on the OAK 4 FFC: luxonis.com/oak4-ffc

Introducing Luxonis OAK 4 FFC

OAK 4 FFC: five camera ports on one 70 x 53 mm RVC4 board. Choose your cameras, place them anywhere, and run depth and AI on board.

luxonis.com
32
xitter.cf/luxonis/status/2115050…
Luxonis | Robotic Vision
@luxonis9h
Introducing OAK 4 FFC, the first OAK Modular device built on OAK 4. Your cameras, wherever the robot needs to see. One board for depth and AI.
27
Luxonis | Robotic Vision retweeted
Open Robotics@OpenRoboticsOrg5h
Win a OAK 4 FFC board-level vision computer from our new Silver OSRA member @Luxonis! To celebrate their membership and the simultaneous release of the OAK 4 FFC, Luxonis is giving away a dev kit to a community member: discourse.openrobotics.org/t…
An image of the OAK 4 FFC. The text on the image reads: ONE BOARD, NOT A STACK A custom multi-camera robot usually takes five vendors and months of glue code. Here it is one board. The usual rig: Compute module and carrier Capture card or deserializer Cameras from another vendor Drivers you maintain Your own sync and calibration OAK 4 FFC RVC4, 52 TOPS on board Five direct MIPI ports Calibrated camera modules DepthAI and Luxonis OS Synced, self-calibrating

ALT An image of the OAK 4 FFC. The text on the image reads: ONE BOARD, NOT A STACK A custom multi-camera robot usually takes five vendors and months of glue code. Here it is one board. The usual rig: Compute module and carrier Capture card or deserializer Cameras from another vendor Drivers you maintain Your own sync and calibration OAK 4 FFC RVC4, 52 TOPS on board Five direct MIPI ports Calibrated camera modules DepthAI and Luxonis OS Synced, self-calibrating

3
2
1
7
894
Learn more and order now: luxonis.com/oak4-ffc

Introducing Luxonis OAK 4 FFC

OAK 4 FFC: five camera ports on one 70 x 53 mm RVC4 board. Choose your cameras, place them anywhere, and run depth and AI on board.

luxonis.com
2
257
Luxonis | Robotic Vision retweeted
Luxonis | Robotic Vision
@luxonisOct 20
Build an OAK app around a VLM in about 15 minutes. One prompt to a coding agent with the Luxonis Agent Toolkit gets you live video, a scene description every 15 seconds from LFM2.5-VL-450M on OAK4, and a searchable history of every frame it saw.
2
1
1
1
448
Luxonis | Robotic Vision retweeted
Luxonis | Robotic Vision
@luxonisOct 8
You can now run vision-language models on OAK4. Ask the camera if a pallet is fully wrapped and get an answer, generated entirely on-device. New llama.cpp and ONNX Runtime support means no conversion step for VLMs and other larger models. Examples are live, more coming soon
6
5
1
13
954
Luxonis | Robotic Vision retweeted
Luxonis | Robotic Vision
@luxonisOct 6
Custom model training now in Luxonis Hub, Part 2: Label your data, train, and convert the model for OAK in one workflow. Here's how each step works! 🧵👇
1
2
9
666
Luxonis | Robotic Vision retweeted
Luxonis | Robotic Vision
@luxonisOct 21
October 27th, 2026.
1
5
1
17
892
October 27th, 2026.
1
5
1
17
892
Test with a prompt, a link to the release, and our MCP installed
Max Mclaughlin
@MaxMclaughlin16Oct 20
Don't want to spend $20k+ to capture accurate point clouds of the items in your bin? Instead, deploy a few OAK 4s running our large Neural Stereo model and fuse their point clouds Full release: discuss.luxonis.com/blog/706…
1
2
465
Release: discuss.luxonis.com/blog/706… MCP: docs.luxonis.com/?install-to…
91
Build an OAK app around a VLM in about 15 minutes. One prompt to a coding agent with the Luxonis Agent Toolkit gets you live video, a scene description every 15 seconds from LFM2.5-VL-450M on OAK4, and a searchable history of every frame it saw.
2
1
1
1
448
Full walkthrough, the exact prompt, and model comparison: discuss.luxonis.com/blog/706…
91
Depth AI 3.11 Release: one pipeline, several OAK 4 cameras. Add cameras with addDevice(), sync their frames, and calibration them into one coordinate system with the new MultiDeviceCalibration node (beta). No calibration target. In depth walkthrough and code: discuss.luxonis.com/blog/706…
1
6
527
You can now run vision-language models on OAK4. Ask the camera if a pallet is fully wrapped and get an answer, generated entirely on-device. New llama.cpp and ONNX Runtime support means no conversion step for VLMs and other larger models. Examples are live, more coming soon
6
5
1
13
954
Full release + examples: discuss.luxonis.com/blog/705…
122
Load more