VLM Run Gateway is a unified platform offering a single OpenAI-compatible endpoint for open-weight OCR and vision-language models, including DeepSeek-OCR-2, GLM-OCR, and dots.mocr. The system manages document orchestration tasks such as PDF rasterization, page distribution, and failure retries, and integrates with the Model Context Protocol for agent-based workflows. It is designed to let teams parse documents at production scale cost-effectively through a standardized API rather than integrating each model separately.
