Equinix Inference Exchange, Built With NVIDIA and Together AI, Due in Q1 2027

What Equinix Inference Exchange combines

Equinix says Inference Exchange is meant to shorten the path from GPU to production inference. The company argues that 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 an environment.

Choosing that location, and connecting it to everything a workload depends on, adds operational complexity at the moment companies need more control and visibility, according to Equinix. Inference Exchange is positioned as the answer to that decision.

The offering combines three elements:

• NVIDIA Enterprise Reference Architectures
• Together AI's inference platform, with more than 200 open-source models
• Equinix data centers connected through Equinix Fabric to the clouds, networks and AI providers that inference relies on

Equinix says this gives customers a faster path from experimentation to production, with secure, low-latency connectivity to the ecosystem they already use.

Who supplies what

Equinix provides the infrastructure: AI-ready data centers with power, advanced cooling and day-two operations, linked through Equinix Fabric to clouds, networks and AI providers.

NVIDIA anchors the build with Enterprise Reference Architectures and accelerated computing. Equinix says these are designed to maximize AI factory throughput and lower token cost.

Together AI runs the inference platform on top. It offers multitenant deployments for shared efficiency, or dedicated single-tenant environments for workloads that need reserved capacity. Because of its OpenAI-compatible API, teams can switch models without rewriting integrations, according to Equinix.

The company also cites its footprint: 280+ data centers, 77 metros, 230 cloud on-ramps and 10,500+ interconnected businesses. It says eight of the top 10 AI model providers and nine of the top 10 AI clouds are deployed with Equinix.

Three intended use cases

Metro edge inference. Companies run inference close to users and data for lower-latency AI experiences, backed by the physical security, operational scale and global reach of Equinix.

Open model migration. Enterprises move production workloads from closed, proprietary models to open-source alternatives. Together AI's platform is reachable over the same Fabric connections used for other providers, which Equinix says lets customers control cost and avoid lock-in.

Sovereign AI. Organizations run AI workloads in locations that meet data residency and sovereignty requirements, with control over where data and inference are processed.

What it means for enterprise buyers

The announcement reflects a shift in enterprise AI from pilots to production, where the question is less which model to use and more where it should run and how it connects to existing clouds and providers. Equinix is betting that a neutral interconnection hub can answer that.

Adaire Fox-Martin, CEO and President of Equinix, said Inference Exchange "will enable architectures that are neutral by design, open by default and engineered for exceptional performance."

Since the service is not due until Q1 2027, the GTC appearance is a chance for prospective customers to discuss placement plans with the Equinix team. The source does not include pricing or detailed availability by region.