Follow Discord
Sweep 28 Sep 2026 · 18:16Z Build v2.1.284 505 read Stable v2.1.277 Latest v2.1.284 Next v2.1.284 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

prompting-claude-sonnet-5 changedbuild-with-claude/prompt-engineering/prompting-claude-sonnet-5

Nearest release: v2.1.284, published 8 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+3added
Lines−7removed
From line 1 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits7to this page, all time

The whole hunk

from line 1, old and new numbered
/
lines
from line 1
11---
22title: Prompting Claude Sonnet 5
33url: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5
4description: Behavioral differences and prompting patterns for Claude Sonnet 5, covering effort, adaptive thinking defaults, tool use, and migration from Claude Sonnet 4.6.
4description: Behavioral differences and prompting patterns for Claude Sonnet 5, covering effort, adaptive thinking defaults, and tool use.
55---
66 
7This guide covers the prompting patterns specific to Claude Sonnet 5. For the model's capabilities and API changes, see [What's new in Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5). For techniques that apply across all current Claude models, see [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).
7This guide covers the prompting patterns specific to Claude Sonnet 5. For the model's specifications, see [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview). For techniques that apply across all current Claude models, see [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).
88 
99Claude Sonnet 5 has particular strengths in coding and agentic tasks. It performs well out of the box on existing Claude Sonnet 4.6 prompts. The patterns in this guide cover the behaviors that most often require tuning.
1010 
11<Note>
12 For API parameter changes when migrating from Claude Sonnet 4.6 (adaptive thinking on by default, sampling parameters not accepted, manual extended thinking removed, and the new tokenizer), see the [migration guide](https://platform.claude.com/docs/en/models/sonnet-5/migration-guide#migrating-from-claude-sonnet-4-6-to-claude-sonnet-5).
13</Note>
14 
1511## Response length and verbosity
1612 
1713Claude Sonnet 5 calibrates response length to the complexity of the task rather than defaulting to a fixed verbosity. This usually means shorter answers on simple lookups and longer ones on open-ended analysis.
from line 53
5753Manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is not supported on Claude Sonnet 5 and returns a 400 error. It was deprecated on Claude Sonnet 4.6 and is now removed. Use adaptive thinking with the effort parameter instead.
5854 
5955<Note>
60 If you are running Claude Sonnet 5 at `high`, `xhigh`, or `max` effort, leave headroom in `max_tokens` so the model has room for thinking and tool calls. On long tasks, adaptive thinking can use a large share of the budget; if the budget is tight, you may see a response that is almost entirely thinking followed by a truncated answer and `stop_reason: "max_tokens"`. Raising `max_tokens` or dropping to `medium` effort resolves this. Because Claude Sonnet 5 uses a [new tokenizer](https://platform.claude.com/docs/en/models/sonnet-5/whats-new-sonnet-5#new-tokenizer) that produces approximately 30% more tokens for the same text, `max_tokens` limits tuned for Claude Sonnet 4.6 may truncate equivalent output. The exact increase depends on the content and workload shape.
56 If you are running Claude Sonnet 5 at `high`, `xhigh`, or `max` effort, leave headroom in `max_tokens` so the model has room for thinking and tool calls. On long tasks, adaptive thinking can use a large share of the budget; if the budget is tight, you may see a response that is almost entirely thinking followed by a truncated answer and `stop_reason: "max_tokens"`. Raising `max_tokens` or dropping to `medium` effort resolves this. Because Claude Sonnet 5 uses a new tokenizer that produces approximately 30% more tokens for the same text, `max_tokens` limits tuned for Claude Sonnet 4.6 may truncate equivalent output. The exact increase depends on the content and workload shape.
6157</Note>
6258 
6359## Tool use triggering
Feedback