# Cloudflare — Cutting our inference bill by 68% by being obsessive about optimization

- Company: Cloudflare (cloudflare.com)
- Announced: 2026-10-19T19:12:53+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://blog.cloudflare.com/obsessive-inference-optimization/
- Record: https://forck.live/items/24719-cutting-our-inference-bill-by-68-by-being-obsessive-about-optimization
- Subject: Cloudflare AI
- Models affected: Claude Opus 4.7

Cloudflare cut the average cost of its AI code review from $2.43 to $0.77, a 68% reduction, after spending rose from $1.19 in April to about $2.46 by late August. The company says most of the increase came from model changes rather than architecture: moving every reviewer onto Anthropic models in early August raised the cost per job from $1.38 to $2.03, and its internal standards reviewer, Codex, went from about $0.25 to $0.88 per review on Claude Opus 4.7. About 40% of the savings came from code changes to the reviewer, with the rest from experimenting with which models it uses and how much effort they put in. Cloudflare found that output tokens were only about 23% of spend, while cache writes cost 43% and cache reads 34%, because each session sent the whole conversation as context. The reviewer now runs on OpenCode v2, a ground-up rewrite that agreed with v1 on the approval decision in 98% of tested merge requests and finishes full-tier reviews about 13% faster. As a side effect of the cost work, the median review now takes 1m 32s instead of 4m 09s.

## Evidence

Verbatim from https://blog.cloudflare.com/obsessive-inference-optimization/:

> With code quality at high effort, the average review now costs just $0.77, down 68% from the $2.43 it averaged over our two most expensive weeks before we started. Our main goal was to cut costs, but as part of this work we also managed to optimize the reviewer, so that the median review now takes just 1m 32s instead of the 4m 09s it took before.

---

Record: https://forck.live/items/24719-cutting-our-inference-bill-by-68-by-being-obsessive-about-optimization
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md