VLM Run
Unified API gateway (Orion) letting developers extract and act on data from images, documents, and video with vision-language models.
What it does
VLM Run is a developer platform offering a single chat-completions-style API, powered by its Orion visual agent, to detect, parse, and reason over images, documents, and video. It combines large vision-language model reasoning with specialized computer-vision tools like OCR, redaction, and object detection, using an OpenAI SDK-compatible interface.
Core features
Single API for images, documents, and video tasks
Object detection, segmentation, and captioning
Structured OCR and document parsing
PHI/PII redaction for healthcare compliance
Drop-in replacement for the OpenAI SDK
Credit-based per-page/per-image pricing
Best for
→Healthcare teams digitizing scanned clinical paperwork
→Construction firms structuring blueprints and specs
→Developers building visual AI agents
→Compliance teams needing auditable data redaction
Pricing
Starter
$0/month
Pro
$799/month