Follow Discord
Sweep 27 Oct 2026 · 19:04Z Build v2.1.312 531 read Stable v2.1.308 Latest v2.1.312 Next v2.1.312 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 27 Oct 2026
One change · api

overview changedmodels/sonnet-5-5/overview

Nearest release: v2.1.312, published under an hour 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+2added
Lines−2removed
From line 26 where the diff opens
First seen 29 Sep 2026 this site's first read of the page
Recorded edits9to this page, all time

The whole hunk

from line 26, old and new numbered
/
lines
from line 26
2626 
2727One more change alters the response shape without failing any request: [text between tool calls comes back in `thinking` blocks](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#text-between-tool-calls). An application that streams that text to its users goes quiet between tool calls until it sets a `display` value that returns the text, or turns off up-front thinking with `between_tools`.
2828 
29[What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5)
29[What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5)
3030 
3131## How it compares
3232 
from line 96
9696 
9797## Good to know
9898 
99* Adaptive thinking is on by default. The lowest thinking setting is `between_tools`, which turns off up-front thinking. It works at `high` effort or below. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).
99* Adaptive thinking is on by default. The lowest thinking setting is `between_tools`, which turns off up-front thinking. It works at `high` effort or below. See [What’s new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#turn-off-up-front-thinking).
100100* Setting `temperature`, `top_p`, or `top_k` returns a 400 error.
101101* The minimum cacheable prompt length is 512 tokens. See [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations).
102102* On the [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing#extended-output-beta), Claude Sonnet 5.5 supports up to 300k output tokens with the `output-300k-2026-03-24` beta header.
Feedback