Checked fact 7888 Oct 2026Money and compute

Anthropic says cache reads make up a large share of models' token consumption, so the cut reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%. Quote: "Because cache reads make up a large share of models’ token consumption, this reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%."

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

Because cache reads make up a large share of models’ token consumption, this reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%.

What the source said when we opened it, on 8 Oct 2026.

The source

Introducing Claude Haiku 5.5
Anthropic · 2026-10-07

Open the source archived copy

Checked

Checked by the notis newsroom on 8 Oct 2026, against the source above.

In the story

Anthropic halves the Sonnet 5.5 cache-read price to $0.10 per million tokens 8 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic says cache reads make up a large share of models' token consumption, so the cut reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%. Quote: "Because cache reads make up a large share of models’ token consumption, this reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%.".” ai notis, checked 8 Oct 2026. Source: Introducing Claude Haiku 5.5 (Anthropic). https://ainotis.com/c/788

As a reference (APA style)

ai notis. (2026, October 8). Anthropic says cache reads make up a large share of models' token consumption, so the cut reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%. Quote: "Because cache reads make up a large share of models’ token consumption, this reduces the cost of Sonnet 5.5 on most agentic tasks by around 20%." [Checked claim 788]. ai notis. https://ainotis.com/c/788

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