Equinix® Inference Exchange, built with NVIDIA and Together AI, shortens the path from GPU to production inference.
Where inference runs now determines its performance, cost and governance. As enterprise AI moves from pilot to production, inference has to sit close to the users, data and applications it serves, across every cloud, model and provider in your environment. Deciding where it runs, and connecting it to everything your workloads depend on, adds operational complexity just as you need more control and visibility.
Equinix Inference Exchange is built for that decision. It combines NVIDIA Enterprise Reference Architectures, Together AI’s inference platform with more than 200 open-source models, and Equinix data centers connected through Equinix Fabric® to the clouds, networks and AI providers your inference relies on. You get a faster path from experimentation to production, with secure, low-latency connectivity to the ecosystem you already use. Equinix Inference Exchange will be available starting in Q1 2027.
Meet with Our Team at NVIDIA GTC
Visit us at NVIDIA GTC Berlin, Hall 7 booth 7037, to see how Equinix Inference Exchange with NVIDIA and Together AI moves AI inference into production.
Schedule a Meeting
How it fits together
Equinix supplies the infrastructure: AI-ready data centers with power, advanced cooling and day-two operations, connected through Equinix Fabric to clouds, networks and AI providers.
NVIDIA anchors the build with Enterprise Reference Architectures and accelerated computing designed to maximize AI factory throughput and lower token cost.
Together AI runs the inference platform on top, with multitenant deployments for shared efficiency or dedicated single-tenant environments for workloads that need reserved capacity. Its OpenAI-compatible API means teams can switch models without rewriting integrations.
Proof line (optional stat band): 280+ data centers | 77 metros | 230 cloud on-ramps | 10,500+ interconnected businesses. Eight of the top 10 AI model providers and nine of the top 10 AI clouds are deployed with Equinix.
Three ways enterprises will use it
Metro edge inference. Run inference close to your users and data for lower-latency AI experiences, backed by the physical security, operational scale and global reach of Equinix.
Open model migration. Move workloads from closed, proprietary models to open-source alternatives in production. Together AI’s platform is reachable over the same Fabric connections you use for your other providers, so you control cost and avoid lock-in.
Sovereign AI. Run AI workloads in locations that meet data residency and sovereignty requirements, with control over where data and inference are processed.
The Coordination Economy: How Enterprises Really Build AI Value
Rather than sheer compute power, AI success depends on proximity, connectivity and ecosystem density.
Read the blog
Equinix Inference Exchange will enable architectures that are neutral by design, open by default and engineered for exceptional performance."Adaire Fox-Martin, CEO and President, Equinix
Additional resources
- Analyst report | Token Optimization Begins with Choice
- Blog | The Coordination Economy: How Enterprises Really Build AI Value
- Product Page | Equinix Inference Exchange
- Product Page Release Notes | Announcing Equinix Inference Exchange
- Press Release | Equinix Accelerates AI Inference for Enterprises with NVIDIA and Together AI
Subscribe to the Equinix Blog