Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

Count tokens in a Message changedapi/messages/count_tokens

Nearest release: v2.1.301, published 11 hours before 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+10added
Lines−0removed
From line 1,185 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits20to this page, all time

The whole hunk

from line 1185, old and new numbered
/
lines
from line 1185
11851185 
11861186 The JSON schema of the format
11871187 
1188- `speed: optional "standard" or "fast" or null`
1189 
1190 The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference.
1191 
1192 Some models require the `fast-mode-2026-02-01` beta header for any `speed` value. See [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode?sdk_languages=http) for which models.
1193 
1194 - `"standard"`
1195 
1196 - `"fast"`
1197 
11881198- `system: optional string or array of TextBlockParam`
11891199 
11901200 System prompt.
Feedback