Checked fact 169417 Oct 2026Agents and apps

For most Claude models, only uncached input tokens count toward input-tokens-per-minute limits; cache_read_input_tokens do not count for most models.

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

Rate limits page: For most Claude models, only uncached input tokens count toward your ITPM rate limits. ... cache_read_input_tokens (tokens read from cache) Do NOT count toward ITPM for most models

What the source said when we opened it, on 17 Oct 2026.

The source

Rate limits
Anthropic

Open the source archived copy

Checked

Checked by the notis newsroom on 17 Oct 2026, against the source above.

In the story

How spend and rate limits cap what an AI agent costs 17 Oct 2026

Cite this fact

Short permanent address

In a sentence

“For most Claude models, only uncached input tokens count toward input-tokens-per-minute limits; cache_read_input_tokens do not count for most models.” ai notis, checked 17 Oct 2026. Source: Rate limits (Anthropic). https://ainotis.com/c/1694

As a reference (APA style)

ai notis. (2026, October 17). For most Claude models, only uncached input tokens count toward input-tokens-per-minute limits; cache_read_input_tokens do not count for most models [Checked claim 1694]. ai notis. https://ainotis.com/c/1694

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