Equinix는 2027년 전용 AI 추론 서비스를 출시하여 전통적인 호스팅을 넘어 관리형 추론 워크로드로 사업을 확장할 계획이다.
Equinix Inc., a digital infrastructure provider, has partnered with NVIDIA and Together AI to launch the Equinix Inference Exchange, a distributed AI inference service for enterprises scheduled for release in the first quarter of 2027.
The service enables organizations to deploy artificial intelligence models closer to end users, business applications, and underlying data, significantly reducing latency during model execution. AI inference—the process by which a trained model applies new data to generate outputs—becomes increasingly critical as companies transition AI initiatives from experimental phases to daily production. This shift requires computing infrastructure capable of scaling with demand while adhering to strict cost, security, and data storage mandates.
Built on NVIDIA’s Enterprise Reference Architectures and Together AI’s inference platform—which supports more than 200 open-source AI models—the service will operate across Equinix’s global network. Customers will access the platform through Equinix data centers and connect seamlessly to cloud providers, telecommunications networks, and AI vendors via Equinix Fabric.
“AI is transforming enterprise technology at extraordinary speed, and the infrastructure decisions enterprises make today will define their competitive position for years to come,” said Adaire Fox-Martin, CEO and president, Equinix. “Equinix is uniquely positioned to deliver what this moment demands based on our nearly three decades building the trusted exchange where the world’s enterprises run, connect, and orchestrate their most critical workloads.”
The platform will offer both multi-tenant shared environments and dedicated infrastructures for organizations requiring isolated compute capacity. By facilitating a migration from proprietary models to open-source alternatives, the service aims to lower operational expenses and mitigate vendor lock-in. Additionally, enterprises in highly regulated sectors can select deployment regions that comply with local data sovereignty and AI processing residency requirements.
“Equinix Inference Exchange turns the world’s leading digital interconnection platform into a global fabric for AI inference,” said Raj Mirpuri, VP of global AI clouds and infrastructure ecosystem at NVIDIA. “As accelerated compute becomes a strategic asset class, combining NVIDIA’s infrastructure and technology with Together AI’s open-model inference platform and Equinix’s global reach gives enterprises a powerful, distributed foundation to bring intelligence closer to their data, applications, and customers, accelerating the next generation of intelligent services.”
“Together AI was built on the conviction that open, accessible AI is what will define the industry moving forward, because enterprises shouldn’t have to choose between model performance and operational flexibility,” said Vipul Ved Prakash, co-founder and CEO, Together AI. “What we are building with Equinix and NVIDIA proves that model choice and performance are not trade-offs. They are the foundation of enterprise AI done right.”
Equinix currently operates more than 280 data centers across 77 metropolitan areas. The partnership and service were officially unveiled at Equinix Horizon, the company’s inaugural customer and partner conference.