Equinix is launching Equinix Inference Exchange through an expanded collaboration with NVIDIA and Together AI. The new service aims to accelerate artificial intelligence for enterprises by providing a faster path from experimentation to production. It utilizes secure, low-latency connectivity to simplify the deployment of distributed AI inference.
The platform combines NVIDIA’s enterprise reference architectures with Together AI’s inference platform. Together AI currently supports over 200 open-source models. This integration aims to make AI deployment more efficient and cost-effective for businesses.
The service will run on Equinix’s global infrastructure of more than 280 data centers. It uses Equinix Fabric to provide connectivity across various clouds and networks. Equinix expects the Inference Exchange to be available in the first quarter of 2027.