Gateway is a ai tools tool built by VLM Run. It's best for Builders and developers integrating visual AI and Enterprises operationalizing visual intelligence. Pricing is usage based.
Pricing
usage based
Audience
Builders and developers integrating visual AI
Community
0%
About Gateway
Gateway is an OpenAI-compatible gateway for visual AI, offering access to 21 visual models through a single chat-completions endpoint.
Gateway by VLM Run provides a unified API for accessing a wide range of visual AI models, including OCR, captioning, detection, segmentation, pose estimation, transcription, and embedding. It supports 21 visual models behind one chat-completions endpoint, making it compatible with existing OpenAI API integrations.
The platform is designed for production visual AI, offering features like orchestration for handling large inputs (e.g., 500-page PDFs or 2-hour videos) by chunking, batching, and reassembling data. It also provides structured outputs with JSON-schema enforcement on every call, ensuring fixed schemas for CV wrappers.
Gateway aims to be a vision-only gateway, distinguishing itself from LLM routers that primarily focus on text models. It offers token and per-image pricing, supports structured outputs, and is BYOK (Bring Your Own Key) ready. The service is built for builders, enabling them to integrate advanced visual AI capabilities into their applications without complex pipeline construction.
Key Features
Pricing
usage basedStarter
- $10 free signup balance
- Up to 10 requests/min
- Community Discord
- Basic Usage Logs
Pro
- $1,000 usage included / month
- Up to 100 requests/min
- Dedicated Slack support
- Zero-Data Retention (ZDR)
- Business Associate Agreement (BAA)
Enterprise
- Tier-based pricing
- Volume discounts
- Custom rate-limits
- Dedicated Slack support
- In-VPC deployments
- Zero-Data Retention (ZDR)
- SOC 2, HIPAA, BAA
- Custom SLAs
Who is it for?
Best for
- Developers needing a unified API for diverse visual AI models
- Companies processing large volumes of documents, images, or videos
- Organizations requiring structured outputs and schema validation for visual data
- Teams looking to reduce costs compared to frontier VLMs and specialized OCR/Document AI APIs
- Industries like Healthcare, Construction, and Physical AI requiring specialized document and image processing
Not ideal for
- Users seeking only text-based LLM solutions
- Individuals or small teams with very low visual AI processing needs who might not benefit from the gateway approach
Integrations
Community Discussion
No discussions yet. Be the first to share your experience!