Equinix Inc., a digital infrastructure company, is working with NVIDIA and Together AI to launch a distributed AI inference service for enterprises in the first quarter of 2027.
Called Equinix Inference Exchange, the service will allow companies to run artificial intelligence (AI) models closer to their users, business applications, and data. This could help reduce delays when AI systems generate answers or perform tasks.
AI inference is the process in which a trained AI model uses new information to produce a result. As companies move AI projects from testing to daily operations, they need computing systems that can handle growing demand while meeting requirements on cost, security, and data storage.
The service will combine NVIDIA’s Enterprise Reference Architectures with Together AI’s inference platform, which supports more than 200 open-source AI models. It will operate through Equinix data centers and connect customers to cloud platforms, networks, and AI providers using 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.”
Equinix said the setup will support shared systems used by several customers and dedicated environments for businesses that require their own computing capacity.
Companies may also use it to move from proprietary AI models to open-source alternatives, which could lower costs and reduce dependence on one provider. Organizations in regulated industries will be able to choose locations that meet rules requiring data and AI processing to remain within a particular country or region.
“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 operates more than 280 data centers across 77 metropolitan areas. The company announced the service at Equinix Horizon, its first customer and partner event.