PINK SOUP
VISUAL INTELLIGENCE AT THE
SPEED OF SIGHT
Our first lightweight visual understanding model built for real hardware. Point, detect, segment, and understand scenes at a speed and cost that makes continuous vision processing finally practical.
Brewed in Lithuania (yes, like the beet soup šaltibarščiai, but way more powerful). Making visual AI accessible, fast, and actually deployable for developers worldwide.
One Model, Many Capabilities
Moondream supports a growing set of visual capabilities - all accessible through natural-language prompts.
Image Captioning
Generate detailed descriptions of complex scenes and objects
Caption:
The image shows a man in a blue jumpsuit and yellow hard hat standing in a large industrial setting. He is wearing safety glasses and ear protection, and is holding a clipboard and a pen, appearing to be taking notes...

Visual Question Answering
Ask natural language questions about any image
Query: Is any vehicle unsecured? Describe.
Yes, there is an unsecured truck parked in the area. The truck is filled with boxes, and it appears to be a delivery truck. The presence of the unsecured truck and the boxes suggests that it might be a delivery service or a delivery truck parked in a public area.

Object Detection
Locate and identify objects with precise bounding boxes
Detect: License plate
(x=0.431, y=0.713, x2=0.569, y2=0.921)

Pointing (x, y)
Pinpoint exact locations in images with coordinate precision
Point: Defect in train tracks.
(x=0.431, y=0.505)

Gaze Detection
Track and analyze where people are looking in real-time
Detect Gaze:
The operator is looking at the bottom-right section of the control panel, near the red warning light.

OCR & Document Understanding
Extract and comprehend text from documents and images
Query: Transcribe the text in natural reading order.
"Preface, The computing world has undergone a revolution since the publication of The C Programming Language in 1978. Big computers are much bigger, and personal computers have capabilities..."

Get Running in Minutes.
Pink Soup is open source and you can install and run it anywhere, for free. You can have it running on your computer or in our cloud in a matter of minutes.
Run It Yourself
- Pink Soup Station is free
- Works with our Python and Node clients
- Works offline, fully under your control
- CPU or GPU compatible
Run in the Cloud
- Spin up instantly - no downloads or DevOps
- $5 in free monthly credits, no card required
- Predictable pay-as-you-go pricing
- 2 RPS on free tier, scales to 10 RPS or more with paid credits
It's Not Just Pink.
It's GENIUS Pink.
Our AI is so smart, it probably knows what you're thinking right now. (Spoiler: You're thinking "wow, this really IS pink soup!")
"Yes, we named our AI after soup. Deal with it." 🥣✨