Shopify cuts Sidekick serving costs 90% with post-trained NVIDIA Nemotron model
90% lower cost
Serving costs down 90% and responses 7x faster, with frontier-level accuracy on internal benchmark
Shopify post-trained an open NVIDIA Nemotron model to run the GraphQL subagent behind its Sidekick merchant assistant. The model matched a leading frontier model's accuracy on an internal benchmark while cutting serving costs 90% and responding seven times faster. Separately, Photoroom's image pipeline helps Vestiaire Collective standardize about 40,000 listing photos daily, with listings…
The tools behind this win
- SidekickShopify merchant assistant whose GraphQL subagent was upgraded
- NVIDIA NemotronOpen model post-trained to power the GraphQL subagent
- PhotoroomImage pipeline standardizing about 40,000 listing photos a day for Vestiaire…