Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 23 Oct 2026
One change · api

effort changedbuild-with-claude/effort

Nearest release: v2.1.309, published 3 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+4added
Lines−3removed
From line 27 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 27, old and new numbered
/
lines
from line 27
2727 Claude API: ga
2828 Claude Platform on AWS: ga
2929 Amazon Bedrock: ga
30 Google Cloud: ga
30 Claude Models on Google Cloud (Google managed): ga
3131 Microsoft Foundry: ga
3232---
3333 
from line 117
117117 Model = Model.ClaudeOpus5_5,
118118 MaxTokens = 4096,
119119 Messages = [
120 new UserMessageParam {
120 new UserMessageParam
121 {
121122 Content = "Analyze the trade-offs between microservices and monolithic architectures"
122123 }
123124 ],
from line 339
338339 
339340To get less thinking, lower the effort level. You can also send `thinking: {"type": "disabled"}` at `high` effort or below. At `xhigh` or `max`, it returns a 400 error, so use adaptive thinking there: omit the `thinking` field or send `thinking: {"type": "adaptive"}`.
340341 
341On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message `output_config`, which preserves the prompt cache. With `thinking: {"type": "disabled"}`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort per turn, use adaptive thinking.
342On the Claude API and Claude Models on Google Cloud (Google managed), Claude Haiku 5.5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message `output_config`, which preserves the prompt cache. With `thinking: {"type": "disabled"}`, effort can't change mid-conversation: a per-message `output_config.effort` that differs from the level in effect returns a 400 error. To vary effort for each turn, use adaptive thinking.
342343 
343344## Effort with tool use
344345 
Feedback