prompting-claude-haiku-5-5 changedbuild-with-claude/prompt-engineering/prompting-claude-haiku-5-5
Recorded here
Lines+5added
Lines−5removed
From line
19
where the diff opens
First seen
8 Oct 2026
this site's first read of the page
Recorded edits8to this page, all time
The whole hunk
from line 19, old and new numbered
/
from line 19
1919* Requests return `stop_reason: "refusal"`: [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-haiku-5-5#safeguard-refusals)
2020
2121<Note>
22 For the breaking API changes when migrating from Claude Haiku 4.5, see the [migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide).
22 For the breaking API changes when migrating from Claude Haiku 4.5, see the [Claude Haiku 5.5 migration guide](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide).
2323
2424 Several sections on this page suggest text to add to your system prompt. Add it to new conversations only. A request that sends thinking blocks back after `system` changed can return a 400 error, so a stored conversation resumed with the new system prompt can fail. To change instructions partway through a conversation, [put them in the newest turn](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#changing-context). On the Claude API, Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), and Claude Models on Google Cloud (Google managed), you can instead [append a system message to the conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#new-instructions).
2525</Note>
from line 38
3838* Thinking is on by default and counts toward `max_tokens`, which can go up to 128,000. A `max_tokens` value sized for Claude Haiku 4.5 requests that ran without thinking can cut the reply off, so leave room for thinking.
3939* To get less thinking, lower the effort level. In Anthropic’s testing, telling the model in the prompt to answer directly didn’t stop it from thinking. You can also turn thinking off with `thinking: {"type": "disabled"}`. This works at `low`, `medium`, and `high` only. At `xhigh` and `max`, the request returns a 400 error.
4040* At `xhigh` effort in multi-turn chats, the model sometimes writes its whole answer in its thinking and ends the turn with no visible text. If you see this behavior, check each response for an empty reply.
41* Changing the top-level `effort` value between requests invalidates the prompt cache for the conversation’s messages. Where your platform supports it, you can change the level partway through a conversation with a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), which keeps the cache. A change holds for every later turn until another one replaces it. It needs the `mid-conversation-output-config-2026-07-01` beta header and adaptive thinking, which is the default. With thinking off, a per-message effort change returns a 400 error.
41* Changing the top-level `effort` value between requests invalidates the prompt cache for the conversation’s messages. Where your platform supports it, you can change the level partway through a conversation with a [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort-per-message) change, which keeps the cache. A change holds for every later turn until another one replaces it. It needs the `mid-conversation-output-config-2026-07-01` beta header and adaptive thinking, which is the default. With thinking off, a per-message effort change returns a 400 error.
4242
4343## Accurate search results
4444
from line 53
5353The model also sometimes needs an extra nudge to search. This occurs most at `low` effort and with long system prompts. To fix it, add this text directly after the date:
5454
5555```text wrap
56Your training data ends well before today's date. Records, office holders, prices, versions, rules and anything "latest" may have changed since then, so search for those before you answer, even when you feel sure. Facts that can't change need no search. When the answer depends on where the user is, put the user's country or region in the search query.
56Your training data ends well before today's date. Records, office holders, prices, versions, rules, and anything "latest" may have changed since then, so search for those before you answer, even when you feel sure. Facts that can't change need no search. When the answer depends on where the user is, put the user's country or region in the search query.
5757```
5858
5959In Anthropic’s testing, this text raised the search rate on questions whose answers had changed. On prompts that need no search, it added searches in only 0–3 percent of tries.
from line 94
9494At `low` and `medium` effort, Claude Haiku 5.5 sometimes reports a code change as done without running a check. If you see the model report results without checking its work, add this paragraph, or one like it, to your system prompt:
9595
9696```text wrap
97When you change code that can be run, built, or type-checked, run a real check that exercises the change before reporting it done: the project's tests, type-checker, or build, or the changed command itself. A syntax-only check, or a check command that failed to start, does not count; if all that is missing is the project's declared dependencies, install them with its own package manager and lockfile (e.g. npm install, pip install -r requirements.txt), never via sudo or the system package manager, unless told not to. Only if no real check can run here, say which one you did not run and why instead of reporting the change as done.
97When you change code that can be run, built, or type-checked, run a real check that exercises the change before reporting it done: the project's tests, type-checker, or build, or the changed command itself. A syntax-only check, or a check command that failed to start, does not count; if all that is missing is the project's declared dependencies, install them with its own package manager and lockfile (for example, npm install or pip install -r requirements.txt), never through sudo or the system package manager, unless told not to. Only if no real check can run here, say which one you did not run and why instead of reporting the change as done.
9898```
9999
100100In Anthropic’s testing, the model checked its changes more often with this text, and its performance improved, at the cost of more tokens.
from line 134
134134
135135If you’re moving from Claude Haiku 4.5, these refusals are new.
136136
137Claude Haiku 5.5 has no [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (beta). If a request is declined, handle `stop_reason: "refusal"` in your client. Sending the same request to Claude Haiku 5.5 again usually returns another refusal.
137Claude Haiku 5.5 has no [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback). If a request is declined, handle `stop_reason: "refusal"` in your client. Sending the same request to Claude Haiku 5.5 again usually returns another refusal.
138138
No line in this hunk matches that.