Equinix has announced Inference Exchange, a new distributed AI inference program it says is designed to help enterprises move AI workloads from experimentation into production.
The company said the initiative expands its collaboration with NVIDIA and adds Together AI as a partner. Under the arrangement, Inference Exchange combines NVIDIA Enterprise Reference Architectures, Together AI’s inference platform—supporting more than 200 open-source models—and Equinix’s global data centre footprint to place inference closer to enterprise data, applications and users.
Equinix said the service will be delivered through its data centres and connect customers to clouds, networks and AI providers via Equinix Fabric. The company argued that as AI deployments scale across models, providers and geographies, the choice of where inference runs has become a key factor affecting performance, cost and governance.
“AI is transforming enterprise technology at extraordinary speed, and the infrastructure decisions enterprises make today will define their competitive position for years to come. 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,” said Adaire Fox-Martin, Chief Executive Officer and President, Equinix.
“Our longtime relationship with NVIDIA delivers the accelerated computing foundation at the heart of modern AI, while Together AI’s commitment to open ecosystems gives enterprises the flexibility to scale on their terms. Equinix Inference Exchange will enable architectures that are neutral by design, open by default and engineered for exceptional performance.”
“Equinix Inference Exchange turns the world’s leading digital interconnection platform into a global fabric for AI inference,” said Raj Mirpuri, vice president of global AI clouds and infrastructure ecosystem at NVIDIA. “As accelerated compute becomes a strategic asset class, combining NVIDIA’s infrastructure & 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 said it has more than 280 data centres across 77 metros, 230 cloud on-ramps and more than 10,500 businesses interconnected on its platform, and claimed eight of the top 10 AI model providers and nine of the top 10 AI clouds are deployed with Equinix.
The company positioned Inference Exchange as supporting a range of use cases, including “metro edge inference” for lower-latency deployments, migration from proprietary models to open-source alternatives, and “sovereign AI” deployments intended to meet data residency and sovereignty requirements.
Equinix said Inference Exchange will be available starting in Q1 2027.
