REDWOOD CITY, CA, Sep 4, 2026 – Equinix has announced Equinix Inference Exchange, a distributed AI inference service for global enterprises built with NVIDIA and Together AI. The service is expected to be available starting in Q1 2027.
The service combines NVIDIA’s Enterprise Reference Architecture with Together AI’s inference platform, which supports more than 200 open-source models. It will run in Equinix’s global data centers and connect to clouds, networks, and AI providers through Equinix Fabric.
How the Service is Built
The service stacks three layers:
- Equinix provides power, advanced cooling, and day-two operations at its data centers.
- NVIDIA provides the Enterprise Reference Architecture and AI infrastructure for the service.
- Together AI runs the platform, supporting multitenant deployments for shared use and single-tenant environments for workloads that need dedicated capacity.
Scale and Connectivity
Equinix operates more than 280 data centers across 77 metros, with 230 cloud on-ramps and more than 10,500 businesses interconnected on its exchange. Eight of the top 10 AI model providers and nine of the top 10 AI clouds are deployed with Equinix. The service will connect to inference providers across major metros worldwide, reducing time-to-first-token.
“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.”
Inference Use Cases
The solution supports a range of enterprise inference scenarios, including:
- Metro edge inference: Runs inference closer to users and data for lower-latency AI experiences, using Equinix’s security, operational scale, and global reach.
- Open model migration: Moves workloads from closed, proprietary models to open-source alternatives to control cost and avoid lock-in. Together AI’s platform is reachable over the same interconnected fabric enterprises already use to reach other providers.
- Sovereign AI: Runs AI workloads in locations that meet data residency and sovereignty requirements for regulated industries and specific geographies, with control over where data and inference are processed.
“Performance, cost and governance have become strategic considerations as AI workloads grow more distributed across providers, data sources and environments,” said Nick Patience, vice president & practice lead, AI Platforms, The Futurum Group. “Organizations are increasingly focused on where inference runs and how quickly it can be deployed into production. Solutions that simplify inference deployment while preserving flexibility will become increasingly important to achieve business outcomes.”
Equinix announced the service at Equinix Horizon alongside Equinix Fabric One, which will make it easier for enterprises to connect across globally distributed AI environments.
Source: Equinix
About Equinix
Equinix is a data center and interconnection company founded in 1998 and based in Redwood City, CA. The company operates data centers worldwide and provides colocation and network connectivity services. Customers use its facilities to house servers, connect to carriers, and exchange data traffic. Equinix serves telecommunications providers, cloud and IT companies, financial institutions, healthcare organizations, and enterprises. Its data centers span North America, Europe and Asia-Pacific. The company serves more than 10,000 customers globally and employs about 13,600 people. Equinix generates revenue by leasing space, power, and cooling capacity, and by providing interconnection services between customers and network providers.
About Together AI
Together AI provides cloud computing and software for training, running and deploying AI models. Founded in 2022, it is headquartered in San Francisco, CA. The company offers serverless, dedicated and batch inference; GPU clusters; code sandboxes; and managed storage. Developers use the platform to train, fine-tune, evaluate and deploy open-source models. Customers can run custom models on dedicated infrastructure or through container services. Together AI serves developers, research organizations, startups, enterprises and software companies. Its customers work in software, media, customer support, health care and financial services. Together AI serves thousands of customers worldwide, including Cursor, Decagon, ElevenLabs, Salesforce, Zoom and Zomato. It also publishes systems research and tools for application programming interfaces.
About NVIDIA
NVIDIA, founded in 1993 and headquartered in Santa Clara, CA, designs and manufactures graphics processing units, systems on chips, networking hardware, and AI intelligence software such as CUDA. Its products serve industries including gaming, data centers, autonomous vehicles, professional visualization, robotics, health care, and energy. The company introduced the GPU in 1999 and later expanded into accelerated computing and AI infrastructure. In gaming, its GPUs support high-performance rendering, while in AI and high-performance computing, its systems provide the infrastructure for training and deploying large-scale models. NVIDIA also develops tools for robotics and autonomous driving.
