Follow Discord
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
Claude Code v2.1.275 ·

$.model.complete maxTokens is now validated against the actual model's output ceiling, not a fixed global cap

$.model.complete's maxTokens limit now matches each model's real output ceiling instead of one fixed number

TierUse it nowhow much it should matter to you
Useful3my rating, 1 to 5
Signal1worth watching, 1 to 5
AreaPlugin APIwhat it touches
KindImprovementsin v2.1.275,
Use it now Notable

$.model.complete's maxTokens limit now matches each model's real output ceiling instead of one fixed number

What

The hook API's $.model.complete previously rejected any maxTokens value above a single hardcoded limit of 8192, regardless of which model was being used. It now looks up the actual output ceiling for the specific model being called (still capped globally at a larger number) and rejects requests that exceed it with 'maxTokens ${s} is past what ${w} can produce in one reply (${O})'.

Why

Models that can produce longer replies than 8192 tokens are no longer artificially capped, while models with smaller limits are still protected from requesting more than they can actually return.

Read from
Names in the bundlemaxTokens
What the documentation says
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since Anthropic's documentation has since written up maxTokens, on preserved-thinking. .maxTokens(16000L) build-with-claude/preserved-thinking see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up maxTokens, on preserved-thinking.

See this entry in the whole of v2.1.275 →

Feedback