# Shopify reports 90% lower serving cost for specialized GraphQL model

_Published Tuesday, October 20, 2026 at 10:27 PM EDT · AI, Products · Latest · Tier 2 — Notable_

![Shopify reports 90% lower serving cost for specialized GraphQL model — Primary](https://cdn.shopify.com/b/shopify-brochure2-assets/53679164e2141bb2849c779d25b2fd4a.png)

Shopify says a specialized open model serving its Sidekick commerce assistant handles GraphQL tasks at about 90% lower serving cost than a frontier model. In replayed production traffic, the post-trained Nemotron 3.5 Lightning model returned complete responses in a median 0.87 seconds, compared with 6.50 seconds for the frontier API.

Shopify trains the specialist using repaired production conversations and evaluates it with a judge calibrated against human labels. After six training loops, its internal score reached 74.5 versus the frontier model's 73. The frontier model still handles merchant conversations, planning and tool selection.

## Sources

- [Shopify Engineering](https://shopify.engineering/open-model-task-experts)

---
Canonical: https://techandbusiness.org/newswire/3l-N9eGfb1IH4Cg9FZOIq3
Published: 2026-10-21T02:27:43.955Z
Story chronology: 2026-10-21T02:12:40.000Z
Retrieved: 2026-10-25T06:20:26.835Z
Publisher: Tech & Business (techandbusiness.org)