Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

optimizing-for-cost-and-intelligence changed

about-claude/models/optimizing-for-cost-and-intelligence

Nearest release: v2.1.280, published 20 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+2added
Lines−2removed
From line 134 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits10to this page, all time

The whole hunk

from line 134, old and new numbered
/
lines
from line 134
134134Most agent requests carry tokens that never influence the answer. Trimming them rarely costs output quality, although not every lever here saved money when measured. Two places to look:
135135 
136136* **Input trimming.** [Dynamic filtering](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool#dynamic-filtering) in the web fetch tool keeps boilerplate out of fetched pages, [image resizing](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size) right-sizes vision inputs, and [tool search with deferred loading](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool) loads tool definitions only when needed (measured later in this section). [Programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) lets Claude run several tool calls from code so only the filtered result enters the context; its documentation reports 24% fewer input tokens on agentic search benchmarks, with a higher score. [Manage tool context](https://platform.claude.com/docs/en/agents-and-tools/tool-use/manage-tool-context) compares tool search, programmatic tool calling, prompt caching, and context editing.
137* **Context lifecycle.** [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) clears stale tool results, and [automatic compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) with its threshold stops long loops from carrying their whole history forward.
137* **Context lifecycle.** [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) clears stale tool results, and [automatic compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) with its threshold stops long loops from carrying their whole history forward.
138138 
139139The levers interact with the cache and each other, so judge them by net effect, and use [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) to confirm your cached prefix survives each change. Anthropic measured them on an issue-triage agent working through 20 real bug reports with screenshots from a public repository, and on a longer variant of the same job with 2.6 times the tokens. With caching on, input trimming (image resizing and tool search) took a further 26% off the short run and 21% off the long one.
140140 
from line 690
690690 ```
691691</CodeGroup>
692692 
693In agent loops the cache-read term is usually the largest of the five; if not, check that caching is engaged. When the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#usage-and-billing) or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction#understanding-usage) is enabled, some tokens are reported only in `usage.iterations` and not in the top-level totals, so sum over `usage.iterations` instead, pricing `advisor_message` entries at the advisor model's rates.
693In agent loops the cache-read term is usually the largest of the five; if not, check that caching is engaged. When the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#usage-and-billing) or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold#understanding-usage) is enabled, some tokens are reported only in `usage.iterations` and not in the top-level totals, so sum over `usage.iterations` instead, pricing `advisor_message` entries at the advisor model's rates.
694694 
695695The following table lists the levers in the order to try them:
696696