Free / Open-sourceBuild, train, and deploy computer vision for the physical world
Free / Open-sourceBuild, train, and deploy computer vision for the physical world
Deepengin records 39 monthly visits with -48.7% month-over-month growth and Contact for Pricing pricing. MixPeek records 33,227 monthly visits with -12.4% growth and Freemium, Contact for Pricing pricing.

All-in-one content moderation API for images and video
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | deepengin.com | mixpeek.com |
| Pricing Model | Contact for Pricing | Freemium, Contact for Pricing |
| Monthly Visits | 39 (39) | 33.23K (33,227) |
| MoM Traffic Delta | -37 (-48.7%) | -4.71K (-12.4%) |
| Primary Market & Share | 🌐 Global (—) | 🇺🇸 United States (28.4%) |
| Direct Visits / mo | 16 | 11.41K |
| User Rating | 3.9 | 4.4 |
| Supported Platforms | Website | Website |

All-in-one content moderation API for images and video
Screen photos, videos and live streams for unwanted content through a single automated API.
Detect nudity, weapons, alcohol, narcotics, offensive gestures and hate symbols without building your own models.
Extract text from images, verify PPE compliance (face, hand and head covers) and run real-time facial similarity matching.
Minimal-code integration with ready-made SDKs and documentation so teams can ship quickly.

A multimodal data warehouse that turns video, audio and documents into queryable rows
Each video, image, audio file or PDF is read where it lives and written as columns such as scene times, descriptions, transcription, OCR text and embeddings — with the producing model named for every column.
Run open embedding, detection, segmentation and video/image Q&A models on your own data, with models compared by task, input type and hardware.
Package models, data and a retrieval strategy into a manifest for a specific job — footage search, video moderation, archive search, article-to-video matching or live RTSP monitoring.
Join your own media against pre-indexed datasets like public figure references, trademark and slogan registries, or the IAB contextual categories to answer questions you could not ask of your files alone.
Free / Open-sourceBuild, train, and deploy computer vision for the physical world
Free / Open-sourceBuild, train, and deploy computer vision for the physical world
Real-time image and video APIs, agentic DAM and creative automation in one platform

Multi-modal AI detection API that flags synthetic images, text, audio, video and deepfakes
Multi-modal AI detection API that flags synthetic images, text, audio, video and deepfakes

Search foundation built from embeddings, rerankers, and reader APIs

Video intelligence infrastructure that makes every second of footage searchable and analyzable
Video intelligence infrastructure that makes every second of footage searchable and analyzable

Natively multimodal AI models and infrastructure for video, image, audio, and text at real-time speed.

OCR and multi-modal document extraction APIs with built-in fraud detection

Agentic document platform that turns messy PDFs into LLM-ready structured data
Agentic document platform that turns messy PDFs into LLM-ready structured data

High-precision document parsing and structured extraction API
High-precision document parsing and structured extraction API

Turn any document into AI-ready Markdown or structured JSON
Turn any document into AI-ready Markdown or structured JSON

One API and workspace for image, video, audio and text models

Agentic document extraction APIs that turn any document into auditable structured data