reduce-latency changedtest-and-evaluate/strengthen-guardrails/reduce-latency
Recorded here
Lines+2added
Lines−2removed
From line
196
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits11to this page, all time
The whole hunk
from line 196, old and new numbered
/
from line 196
196196 ```
197197</CodeGroup>
198198
199For more details about model metrics, see the [models overview](https://platform.claude.com/docs/en/models/overview) page.
199For more details about model metrics, see [Models overview](https://platform.claude.com/docs/en/models/overview).
200200
201201### 2. Optimize prompt and output length
202202
from line 219
219219
220220 `max_tokens`
221221
222 tokens, the response will be cut off, perhaps mid-sentence or mid-word, so this is a blunt technique that might require post-processing and is usually most appropriate for multiple choice or short answer responses where the answer comes right at the beginning.
222 tokens, the API cuts it off, perhaps mid-sentence or mid-word. This is a blunt technique that might require post-processing. It’s usually most appropriate for multiple-choice or short-answer responses where the answer comes right at the beginning.
223223 </Note>
224224
225225Finding the right balance among prompt clarity, output quality, and token count might require some experimentation.
No line in this hunk matches that.