effort changedbuild-with-claude/effort
Nearest release: v2.1.307, published an hour after 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+9added
Lines−9removed
From line
199
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits17to this page, all time
The whole hunk
from line 199, old and new numbered
/
from line 199
199199 client = Anthropic::Client.new
200200
201201 message = client.messages.create(
202 model: "claude-opus-5-5",
202 model: Anthropic::Model::CLAUDE_OPUS_5_5,
203203 max_tokens: 4096,
204204 messages: [
205205 { role: "user", content: "Analyze the trade-offs between microservices and monolithic architectures" }
from line 229
229229* Tool calls and function arguments
230230* Thinking (when active)
231231
232Because effort applies to every output token, it works whether or not thinking is enabled. Lower effort also means fewer and terser tool calls.
232Because effort applies to every output token, it works with or without thinking. Lower effort also means fewer and terser tool calls.
233233
234234### Effort levels
235235
from line 301
301301| `xhigh` | The recommended starting point for coding and agentic work, and for exploratory tasks such as repeated tool calling, detailed web search, and knowledge-base search. Expect meaningfully higher token usage than `high`. |
302302| `max` | Reserve for frontier problems. On most workloads `max` adds significant cost for relatively small quality gains, and on some structured-output or less intelligence-sensitive tasks it can lead to overthinking. |
303303
304Claude Opus 4.7 also respects effort levels more strictly than Claude Opus 4.6, especially at `low` and `medium`. At lower effort levels, the model scopes its work to what was asked rather than doing more than requested. If you observe shallow reasoning on complex problems with Claude Opus 4.7, raise effort rather than prompting around it. If you must keep effort low for latency, add targeted guidance like "This task involves multistep reasoning. Think carefully before responding."
304Claude Opus 4.7 also respects effort levels more strictly than Claude Opus 4.6, especially at `low` and `medium`. At lower effort levels, the model scopes its work to what was asked rather than doing more than requested. If you observe shallow reasoning on complex problems with Claude Opus 4.7, raise effort rather than prompting around it. If you must keep effort low for latency, add targeted guidance such as "This task involves multistep reasoning. Think carefully before responding."
305305
306306When running Claude Opus 4.7 at `xhigh` or `max` effort, set a large `max_tokens` so the model has room to think and act across subagents and tool calls. Starting at 64k tokens and tuning from there is a reasonable default.
307307
from line 311
311311
312312To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It's the lowest thinking setting on Claude Sonnet 5.5, and it works at `low`, `medium`, and `high` effort. At `xhigh` or `max`, a request with it returns a 400 error, so use adaptive thinking at those levels: omit the `thinking` field or send `thinking: {"type": "adaptive"}`. See [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking).
313313
314Claude Sonnet 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 `between_tools`, 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. See [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#calibrate-effort).
314Claude Sonnet 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 `between_tools`, 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. See [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#calibrate-effort).
315315
316316### Recommended effort levels for Claude Sonnet 5
317317
from line 327
327327
328328Sonnet 4.6 defaults to `high` effort. Explicitly set effort when using Sonnet 4.6 to avoid unexpected latency:
329329
330* **Medium effort** (recommended default): Best balance of speed, cost, and performance for most applications. Suitable for agentic coding, tool-heavy workflows, and code generation.
330* **Medium effort (recommended default):** Best balance of speed, cost, and performance for most applications. Suitable for agentic coding, tool-heavy workflows, and code generation.
331331* **Low effort:** For high-volume or latency-sensitive workloads. Suitable for chat and non-coding use cases where faster turnaround is prioritized.
332332* **High effort:** For complex reasoning and tasks where quality matters more than speed or cost.
333333* **Max effort:** For tasks requiring the absolute highest capability with no constraints on token spending.
from line 349
349349* Proceed directly to action without preamble
350350* Use terse confirmation messages after completion
351351
352Higher effort levels may:
352Higher effort levels might:
353353
354354* Make more tool calls
355355* Explain the plan before taking action
from line 374
374374
375375Per-message effort is in beta. On the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), it's available on Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, and Claude Haiku 5.5. On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it's available on Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5.5. It requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. With the Amazon Bedrock [InvokeModel API](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), it's available on Claude Fable 5.1 and Claude Opus 5.5, and you send that value in the `anthropic_beta` array of the request body instead.
376376
377Without the beta value, a per-message `output_config` returns a 400 error: `messages.N.output_config: Extra inputs are not permitted`, where `N` is the index of the `system` message in `messages`. With the beta value, models without per-message effort, including Claude Fable 5, return a 400 error: `output_config.effort requires a model that supports per-turn effort; this model does not`. On Amazon Bedrock, those models and Claude Opus 5 return the `Extra inputs are not permitted` error instead. On Claude Sonnet 5.5 with `thinking: {"type": "between_tools"}` and on Claude Haiku 5.5 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.
377Without the beta value, a per-message `output_config` returns a 400 error: `messages.N.output_config: Extra inputs are not permitted`, where `N` is the index of the `system` message in `messages`. With the beta value, models without per-message effort, including Claude Fable 5, return a 400 error: `output_config.effort requires a model that supports per-turn effort; this model does not`. On Amazon Bedrock, those models and Claude Opus 5 return the `Extra inputs are not permitted` error instead. On Claude Sonnet 5.5 with `thinking: {"type": "between_tools"}` and on Claude Haiku 5.5 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.
378378
379379Add a `role: "system"` message with empty `content` and the new level in `output_config.effort`. Placed directly after a `user` turn with new input, it sets the level for Claude's reply to that turn. Placed anywhere else, such as between an `assistant` turn and the next `user` turn as in the following example, it takes effect from the next `user` turn with new input. A `user` turn that holds only `tool_result` blocks doesn't count as new input, so a change placed after one in a tool-use loop waits for the next `user` turn with new input. The new level then holds until a later message changes it. Everything before that message is unchanged, so the cached prefix still matches.
380380
from line 627
627627 client = Anthropic::Client.new
628628
629629 response = client.beta.messages.create(
630 model: "claude-fable-5-1",
630 model: Anthropic::Model::CLAUDE_FABLE_5_1,
631631 max_tokens: 4096,
632632 output_config: {effort: :high},
633633 messages: [
from line 659
6596591. **Set effort explicitly:** The API defaults to `high` (`medium` on Claude Opus 5.5 and Claude Haiku 5.5), but the right starting point depends on your model and workload.
6606602. **Use low for speed-sensitive or simple tasks:** When latency matters or tasks are straightforward, low effort can significantly reduce response times and costs.
6616613. **Test your use case:** The impact of effort levels varies by task type. Evaluate performance on your specific use cases before deploying.
6624. **Consider dynamic effort:** Adjust effort based on task complexity. Simple queries may warrant low effort while agentic coding and complex reasoning benefit from high effort. See the next item before varying it within one conversation.
6624. **Consider dynamic effort:** Adjust effort based on task complexity. Simple queries might warrant low effort, whereas agentic coding and complex reasoning benefit from high effort. See the next item before varying it within one conversation.
6636635. **Hold top-level effort constant within cached conversations:** Changing the top-level effort value between requests invalidates [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), so vary it across workloads rather than within a conversation that relies on cache hits. On models that support it, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) instead, which preserves the cache. See [Thinking and prompt caching](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-prompt-caching).
664664
665665## Next steps
No line in this hunk matches that.