Official RPi AI Camera, 12MP, IMX500 Intelligent Vision Sensor, 78.3° FOV, Based on IMX500 Intelligent Vision Sensor, AI Camera Compatible with Raspberry Pi 5/ 4B/3B+/3B/2B/A+/Zero W/WH/Zero 2W

The RPi AI Camera is a compact camera module from RPi, based on 12.3MP IMX500 Intelligent Vision Sensor, with a powerful neural network accelerator.
IMX500 combines a 12.3MP CMOS image sensor with onboard inferencing accelerator for a variety of common neural network models, enabling users to develop sophisticated vision-based AI applications without the need for a separate accelerator.
The AI Camera transparently augments captured still image or video with tensor metadata, leaving the processor in the host RPi free to perform other operations. Support for tensor metadata in the libcamera and Picamera2 libraries, and in the rpicam-apps application suite, make it easy for beginners to use, while offering advanced users unparalleled power and flexibility.
The RPi AI Camera is compatible with Raspberry Pi Boards (All Versions). The PCB outline and mounting hole locations are identical to those of RPi Camera Module 3, while the overall depth is greater to accommodate the larger IMX500 sensor and optical subassembly.
Framerates: 2×2 binned: 2028×1520 10-bit 30fps. Full resolution: 4056×3040 10-bit 10fps. FoV: 78.3°±3°, with manual/mechanical adjustable focus. Focal ratio: F1.79.