Equinix puts 200 open models on inference exchange

Equinix announced an Inference Exchange for Q1 2027 that combines NVIDIA enterprise reference architectures, Together AI’s inference platform for more than 200 open-source models, and Equinix’s global data-center network, the company said. Equinix says its footprint spans more than 280 data centers across 77 metros, 230 cloud on-ramps, and 10,500 interconnected businesses; those are scale claims, not a latency or cost benchmark. For operators weighing the cost of placing AI capacity, the signal is a routing layer for open-model migration and sovereign inference—measure time-to-first-token and all-in cost before committing to Q1 availability.