---
format: "aidr-story-markdown/v1"
id: "bfaf20be2cbb21bd3f0e1f546c8d9bf81d193a95247954bf5ce62224ec50d714"
canonical_url: "https://aidr.today/bfaf20be?lang=en"
title: "Revolut Cuts AI Token Costs by 90% With Shift to Self-Hosted GLM for Engineering"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-03T08:07:29.000Z"
category: "Tools"
topics: ["coding","devtools"]
source_urls: ["https://x.com/guilleflorvs/status/2117379073785696395"]
summary: "Revolut transitioned approximately 2,000 engineers to a self-hosted GLM model for coding. The system runs on 56 Nvidia B200 GPUs and costs a blended 30 cents per million tokens. The shift to an internal model reduced engineering lead time by 70%."
---

# Revolut Cuts AI Token Costs by 90% With Shift to Self\-Hosted GLM for Engineering

> [Open the canonical story](<https://aidr.today/bfaf20be?lang=en>)

**Published:** 2026-11-03T08:07:29.000Z
**Category:** Tools
**Topics:** coding, devtools

## Summary

Revolut transitioned approximately 2,000 engineers to a self\-hosted GLM model for coding\. The system runs on 56 Nvidia B200 GPUs and costs a blended 30 cents per million tokens\. The shift to an internal model reduced engineering lead time by 70%\.

## Sources

- [Supporting source](<https://x.com/guilleflorvs/status/2117379073785696395>)