Equinix is expanding its collaboration with NVIDIA and partnering with Together AI to launch Equinix Inference Exchange, a distributed AI inference program designed to help enterprises deploy AI workloads closer to their data, applications and users.
The solution combines NVIDIA Enterprise Reference Architectures, Together AI’s inference platform supporting more than 200 open-source models, and Equinix’s global data center and interconnection infrastructure. Through Equinix Fabric, enterprises will be able to connect inference workloads with clouds, networks and AI providers across multiple locations.
The technology is designed to address growing enterprise demand for AI inference that can deliver lower latency, improved performance, cost efficiency and greater control over where AI workloads run.
Equinix said the platform will support several enterprise use cases, including metro-edge inference, open-model migration and sovereign AI. Running inference closer to users and data can enable more responsive AI applications, while support for open models can help organizations reduce vendor lock-in and manage costs.
For regulated industries and organizations with data residency requirements, the distributed architecture can also provide greater control over the locations where data and AI inference are processed.
Equinix currently operates more than 280 data centers across 77 metros, with 230 cloud on-ramps and more than 10,500 interconnected businesses. The company said eight of the top 10 AI model providers and nine of the top 10 AI clouds are deployed with Equinix.
Equinix Inference Exchange is scheduled to become available in Q1 2027.
