# VLM Run

> The unified gateway for document, image, and video AI. Open-weight vision models behind one OpenAI-compatible API — Orion, our visual agent, sees, reasons, and acts when you need more than raw models.

Key terms: Visual Intelligence, Vision-Language Model, VLM, Orion, Visual Agent, Document OCR, Structured Output, Visual Grounding, HIPAA, SOC 2, Computer Vision, Multimodal AI, Visual ETL, API

## Product

- [Homepage](https://vlm.run): The unified gateway for document, image, and video AI. Open-weight vision models behind one OpenAI-compatible API.
- [Product](https://vlm.run/product): Build, run, and operate visual AI across images, documents, and video with production-grade accuracy, observability, and control.
- [Orion Visual Agent](https://vlm.run/orion): Orion, the visual agent that sees, reasons, and acts on images, video, and documents through a single OpenAI-compatible API.
- [Gateway](https://vlm.run/gateway): The OpenAI-compatible gateway for visual AI. OCR, captioning, detection, and chat behind one endpoint.
- [Gateway Models](https://vlm.run/gateway/models): Visual models on the VLM Run Gateway: OCR, markdown, captioning, detection, and embeddings behind one OpenAI-compatible endpoint.
- [Routed Models](https://vlm.run/gateway/models/routed-models): Frontier models the gateway routes to an upstream provider, so one key and one OpenAI-compatible endpoint cover them as well.
- [Document AI](https://vlm.run/doc-ai): Document intelligence for the agentic stack. Schema-validated JSON with grounding from PDFs and scans.
- [Image AI](https://vlm.run/product/images): Caption, detect, segment, and generate images through one OpenAI-compatible API.
- [Video AI](https://vlm.run/video-ai): Summarize, transcribe, and search video with time-anchored structured output.
- [Physical AI Demo](https://vlm.run/demos/physical-ai): Side-by-side Orion dense segmentation on robot padlock-unlock episodes.
- [Pricing](https://vlm.run/pricing): Dollar billing for Orion agents, models, and tools. Start free with a $10 balance.
- [Chat Playground](https://chat.vlm.run): Try Orion in a hosted chat interface.
- [API Docs](https://docs.vlm.run): Developer documentation, API reference, and quickstart guides.

## Documentation

- [Documentation llms.txt](https://docs.vlm.run/llms.txt): Machine-readable index of all docs pages with markdown URLs for AI crawlers and agents.
- [Docs Introduction](https://docs.vlm.run/introduction): What VLM Run is and how to extract structured JSON from images, video, and documents.
- [Ways to Use VLM Run](https://docs.vlm.run/ways-to-use-vlm-run): Requests, Executions, Chat Completions API, and Chat UI — when to use each entry point.
- [Orion Agents](https://docs.vlm.run/agents/introduction): VLM Run Orion visual agent: sees, reasons, and acts on images, video, and documents.
- [API Pricing (Docs)](https://docs.vlm.run/pricing): Dollar API pricing: token rates, fixed-price tools, grounding, service tiers, and examples.
- [Parsing Invoices Guide](https://docs.vlm.run/guides/doc-ai/guide-parsing-invoices): Step-by-step guide to extract structured invoice data from PDFs and images.

## Solutions

- [Healthcare](https://vlm.run/solutions/healthcare): Healthcare document AI: parse handwritten intakes, extract histories, triage mixed faxes, and cite lab values as HIPAA-ready JSON for your EHR.
- [Construction](https://vlm.run/solutions/construction): Construction drawing AI: parse blueprints, drawing sets, door schedules, and spec sections into structured JSON for takeoffs and submittal review.
- [Insurance](https://vlm.run/solutions/insurance): Automate claims processing without brittle OCR. Extract, reason, and validate claims data across documents and images.
- [Real Estate](https://vlm.run/solutions/real-estate): Make property data usable instantly. Extract lease terms, normalize rent rolls, and analyze listing images.
- [Media & Entertainment](https://vlm.run/solutions/media-entertainment): Make massive media libraries searchable. Auto-tag, index, and summarize images and video at scale.
- [SaaS](https://vlm.run/solutions/saas): Turn session recordings into structured UX insights. Understand video without watching it.
- [Multimodal Intelligence](https://vlm.run/solutions/multimodal-intelligence): Deploy and orchestrate vLLM and vision models through one production API without building the stack.

## Open Source

- [vlmrun-hub](https://vlm.run/open-source/vlmrun-hub): Production-ready Pydantic schemas for Visual ETL. Extract structured, validated data from any VLM.
- [vlmbench](https://vlm.run/open-source/vlmbench): Benchmark any vision-language model on your hardware with a single command.
- [mm](https://vlm.run/open-source/mm): Fast multimodal context for agents. UNIX-style tools with multimodal powers.
- [autovllm](https://vlm.run/open-source/autovllm): Optimized vLLM for production VLM inference with LRU caching and Triton kernel fusions.

## Resources

- [Blog](https://vlm.run/blog): Case studies, product updates, and technical posts from VLM Run.
- [FAQ](https://vlm.run/faq): Answers about Orion, pricing, healthcare, construction, security, and enterprise deployment.
- [About](https://vlm.run/about): VLM Run builds the gateway towards visual intelligence for enterprise teams.
- [Orion Whitepaper](https://storage.googleapis.com/vlm-data-public-prod/web/assets/vlmrun-orion-whitepaper-latest.pdf): Technical overview of Orion architecture and capabilities.

## Developers

- [Cookbooks](https://github.com/vlm-run/vlmrun-cookbook): Example workflows and integration patterns for the VLM Run API.
- [Discord](https://discord.gg/AMApC2UzVY): Community support and product discussion.
- [GitHub](https://github.com/vlm-run): Open-source repositories, SDKs, and cookbooks.

## Company

- [Trust Center](https://trust.vlm.run): SOC 2, HIPAA, security, and compliance documentation.
- [Careers](https://app.dover.com/VLM%20Run/careers/a63ca8a3-0866-4a36-88a7-b755a9b4aef3): Open positions at VLM Run.

## Optional

- [RSS Feed](https://vlm.run/blog/feed.xml): Blog syndication feed.
- [Introducing the VLM Run Gateway: Unified API for Visual Intelligence](https://vlm.run/blog/introducing-gateway): One OpenAI-compatible endpoint for specialized VLMs. Swap models in a line, and stop paying frontier prices to read images, documents and videos.
- [Orion 2: Frontier Visual Agents with Code Execution](https://vlm.run/blog/orion-2): Orion 2, our most capable visual agent, writes and executes vision programs on the fly – faster, cheaper, more reliable.
- [How Scan.com Automates Document Workflows with VLM Run's Orion](https://vlm.run/blog/scan-com-case-study): How Scan.com Automates Document Workflows with VLM Run's Orion
- [Introducing Artifacts Support for Orion](https://vlm.run/blog/introducing-orion-artifacts): Explore VLM Run's new visual Agent with Artifacts
- [Automating PII and PHI Compliance with VLM Run’s Redaction API](https://vlm.run/blog/document-redaction): VLM Run's redaction API automatically detects and removes PII and PHI from sensitive documents. Ensure HIPAA, PCI DSS, and GDPR compliance across healthcare, finance, and legal workflows while protecting enterprise data.

## FAQ

### Product & Orion

#### How is Orion different from GPT-5, Claude, or Gemini?

Frontier models can describe what they see, but not act on it. Orion goes beyond perception by planning, executing, and validating visual tasks. Instead of just describing an image, Orion can detect, crop, segment, generate, and analyze in sequence, reliably and deterministically.

#### What can I build with Orion?

Developers use Orion for visual ETL pipelines, automated product and marketing asset generation, document parsing and redaction, video summarization and clipping, medical and geospatial visual analysis, UI testing, and more.

#### How accurate is Orion compared to traditional CV models?

Orion combines modern VLM architectures with traditional computer-vision models. In benchmarks across multi-modal tasks, Orion consistently outperforms leading VLMs on multi-step visual reasoning, structured OCR, and traditional CV tasks.

#### Can VLM Run handle handwritten and scanned documents?

Yes. Orion reasons visually about layout and structure, not just flat text. It handles messy scans, faxes, handwritten forms, and complex table layouts that traditional OCR struggles with.

### Pricing & Billing

#### How is Orion priced?

Credits start at $0.01 each (100 credits = $1) with 1,000 free sign-up credits. See https://vlm.run/pricing for tier breakdowns and per-domain rates.

#### Is there a free trial?

Yes. Every account starts with 1,000 free credits ($10) and no card required. Upgrade to Pro or Enterprise whenever you need more throughput or compliance.

#### Do unused credits roll over?

Pro plan credits are replenished monthly and don't roll over. Overage credits are billed on demand at the standard rate.

#### When should I use visual grounding?

Use grounding when you need an audit trail. Grounding returns bounding boxes and confidence scores for every extracted field, required for healthcare, finance, and legal QA workflows.

#### Can I mix service tiers within one project?

Yes. Set the tier per request so real-time user calls can use priority while nightly batches use flex, all from the same API key.

#### How does billing work for multi-page PDFs?

Each page is billed independently at the configured detail level. A 20-page PDF at auto = 2 × 20 = 40 credits ($0.40). Grounding adds +2 per page.

#### What's included in Zero-Data Retention?

With ZDR enabled (Pro and Enterprise), your files and API responses are never persisted on our infrastructure. Processing happens in memory and results stream directly back to you.

#### What payment methods do you accept?

We bill through Stripe (Visa, Mastercard, American Express). Enterprise customers can arrange invoice billing with custom net terms.

### Healthcare

#### What types of documents do you support today?

Common healthcare documents including referrals, intake forms, insurance cards, faxes, claims packets, and EOBs, structured for EMR/EHR and FHIR workflows.

#### Can you handle faxed or low-quality scanned documents?

We handle scanned PDFs, faxed referrals, handwritten or typed forms, insurance card photos, and multi-page claims. If we don't support something yet, we can often add it in under 24 hours.

#### Is this production-ready for healthcare?

Yes. HIPAA-ready deployments, private VPC hosting, audit logging, and schema-level validation for regulated workflows like referrals and claims.

#### How is this different from OCR or generic LLM APIs?

Text-based OCR and generic LLM APIs primarily read text. VLM Run uses vision-language models to reason about layout, structure, and relationships, then enforces deterministic healthcare schemas on top.

### Construction

#### Can VLM Run handle low-quality scans and blueprints?

Yes. Our models handle faded scans, hand-marked drawings, low-res PDFs, and on-site photos. Orion reasons visually about layout and structure, not just characters.

#### What document types does VLM Run support?

Blueprints, floorplans, schedule tables, BOQs, material lists, submittals, RFIs, and spec sheets including merged cells, nested headers, and multi-page tables.

#### How does VLM Run compare to traditional OCR for construction documents?

Traditional OCR fails on complex table layouts, drawing symbols, and engineering annotations. VLM Run uses vision-native models trained on technical documents to reason about structure.

#### Is my project data secure?

VLM Run is SOC 2 Type II certified. Enterprise customers can use VPC deployment so data never leaves your cloud. All data is encrypted in transit and at rest.

### Security & Enterprise

#### How do you keep data private?

Pro-tier runs in our private cloud with API logging in the observability dashboard. Enterprise-tier supports SOC 2, GDPR, and HIPAA with configurable retention including ZDR.

#### Can I run Orion on-prem or in-VPC?

Yes. Enterprise deployments support VPC Peering and In-VPC hosting so data never leaves your environment. SOC 2 Type II and HIPAA-ready.

#### Can I upgrade or downgrade my plan anytime?

Yes. Changes take effect immediately with prorated billing. Enterprise plans include invoice billing and custom SLAs.