Checked fact 196620 Oct 2026AI at work

The post says the first request of a session found a cached prefix only 14% to 26% of the time, although every session starts with the same tool definitions and agent prompt of between 11k and 21k tokens.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

The data showed that the first request of a session found a cached prefix only 14% to 26% of the time. Every session starts with the same tool definitions and the same agent prompt, between 11k and 21k tokens that are identical in every repository we review

What the source said when we opened it, on 20 Oct 2026.

The source

Cutting our inference bill by 68% by being obsessive about optimization
Cloudflare Blog · 2026-10-19

Open the source archived copy

Checked

Checked by the notis newsroom on 20 Oct 2026, against the source above.

In the story

Cloudflare says its AI code reviews now cost 68% less 20 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The post says the first request of a session found a cached prefix only 14% to 26% of the time, although every session starts with the same tool definitions and agent prompt of between 11k and 21k tokens.” ai notis, checked 20 Oct 2026. Source: Cutting our inference bill by 68% by being obsessive about optimization (Cloudflare Blog). https://ainotis.com/c/1966

As a reference (APA style)

ai notis. (2026, October 20). The post says the first request of a session found a cached prefix only 14% to 26% of the time, although every session starts with the same tool definitions and agent prompt of between 11k and 21k tokens [Checked claim 1966]. ai notis. https://ainotis.com/c/1966

Anyone may quote this address. It does not change; if we correct the story, this page says so.