Flex Engine adds MinerU, PaddleOCR, and selected ML models, alongside simpler resource management
SINGAPORE, Sept. 17, 2026 /PRNewswire/ — Arcfra today announced Neutree 1.2, a new release that expands model support and simplifies resource planning and operations management for enterprise AI platforms.
Neutree 1.2 introduces Flex Engine, an Arcfra-developed inference engine that supports non-LLM models such as MinerU and PaddleOCR. Building on standard inference engines such as vLLM and SGLang, users can manage language, multimodal, embedding, rerank, document parsing, OCR, and machine learning models on one platform, then publish and manage service calls through Neutree’s unified model gateway. This reduces duplicated platform work and accelerates the path from model validation to business use.
Visual model registry management improves model asset visibility. Neutree 1.2 supports unified management of public and private models, showing source, connection status, visibility, model count, storage usage, and update time in one interface, along with each model’s parameter count, size, and precision.
Automatic KV-cache and GPU memory calculation makes deployment predictable. The platform parses model structure and calculates the KV-cache required for a deployment based on the user’s context window and concurrency settings, then recommends the GPU memory needed, reducing the risk of failed deployments and avoiding unnecessary GPU memory waste.
The platform also adds project-based API key management, letting users group multiple API keys by business project and identify ownership through the project name and description. Keys are shown with their workspace, status, usage, rate limit, supported models, and creation time, with search and filtering. This shifts API key management from a simple key list to a business-oriented view, clarifying business ownership across teams.
Through standardized model delivery, unified compute and model management, model governance, gateway management, and end-to-end observability, Neutree helps enterprises move from deploying models to unified governance across models, compute, and applications. Together with Arcfra Enterprise Cloud Platform, enterprises can build production-grade, governable model inference infrastructure.
Several customers have started using Neutree. A manufacturing leader used its existing Arcfra infrastructure as a production-grade AI foundation to streamline model delivery and unify compute and model resource management, and a shipbuilding customer brought compute management, model management, and the model gateway into a single platform, enabling faster model rollout, unified access, and visual observability.
Neutree 1.2 is now open source on GitHub. For Neutree Enterprise, please contact the Arcfra team.