One read of Claude Developer Platformapi-20261111T173709Z
134 pages moved out of 901 read.
Pages moved
134
significant first
Pages read
901
in this capture
Captured
17:37 UTC
Corpus hash
1ddc0440424a
corpus-hash
What this read moved
1-25 of 134, page 1 of 6This capture is too large to show at once. Changes 1-25 of 134 are below, significant first; the rest are on the following screens.
about-claude/models/choosing-a-model Changed · +5 / -5 lines
from line 11
1111* **Capabilities:** What specific features or capabilities will you need the model to have to meet your needs?
1212* **Speed:** How quickly does the model need to respond in your application? [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) delivers up to 2.5x higher output speed at premium pricing on [supported models](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
1313* **Cost:** What’s your budget for both development and production usage?
14* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Fable 5.2, Claude Fable 5.1, Claude Opus 5, and Claude Sonnet 5.5, start with the default (`high`) and adjust up or down based on your evals. On Claude Opus 5.5 and Claude Haiku 5.5 the default is `medium`; start there and adjust the same way. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.
14* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Fable 5.2, Claude Fable 5.1, Claude Opus 5, and Claude Sonnet 5.5, start with the default (`high`) and adjust up or down based on your evals. On Claude Opus 5.5 and Claude Haiku 5.5, the default is `medium`; start there and adjust the same way. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.
1515
1616***
1717
from line 43
43432. [Optimize your prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5) for this model.
44443. Evaluate if performance meets your requirements.
45454. Consider increasing efficiency by lowering [effort](https://platform.claude.com/docs/en/build-with-claude/effort) or downgrading models over time with greater workflow optimization.
465. If your evals at `xhigh` or `max` effort still fall short on demanding reasoning or long-horizon agentic work, move to [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2).
465. If your evals at `xhigh` or `max` effort still fall short on demanding reasoning or long-horizon agentic work, move to [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview).
4747
4848This approach is best for:
4949
from line 57
5757
5858**Claude Fable 5.2** (`claude-fable-5-2`) is Anthropic’s most capable model open to all customers. It’s built for demanding reasoning and long-horizon agentic work. **Claude Mythos 5.2** (`claude-mythos-5-2`) offers the same capabilities only to organizations verified through Anthropic’s verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). Both models use always-on [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). If your code changes `system`, `tools`, or earlier messages in a conversation, moves a conversation between models, uses the `computer_20251124` computer use tool, or uses the advisor tool, see [Claude Fable 5.2 breaking changes](https://platform.claude.com/docs/en/models/fable-5-2/whats-new-fable-5-2#breaking-changes) before switching.
5959
60For context windows, output limits, and prices, see the [model comparison table](https://platform.claude.com/docs/en/models/overview#latest-models-comparison).
60For context windows, output limits, and prices, see the [All models](https://platform.claude.com/docs/en/models/overview#all-models) table.
6161
6262## Model selection matrix
6363
from line 74
7474
7575## Decide whether to upgrade or change models
7676
77To determine if you need to upgrade or change models, you should:
77To decide whether to upgrade or change models:
7878
79791. [Create benchmark tests](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) specific to your use case. Having a good evaluation set is the most important step in the process.
8080
from line 90
9090
9191## Combine models
9292
93Multi-model strategies pair a lower-cost model with a frontier model so that most tokens are billed at the lower rate. The two common patterns are an executor that escalates hard decisions to an advisor, and an orchestrator that delegates bulk work to lower-cost workers. See [Optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence) for both strategies, measured examples, and implementation options.
93Multimodel strategies pair a lower-cost model with a frontier model so that most tokens are billed at the lower rate. The two common patterns are an executor that escalates hard decisions to an advisor, and an orchestrator that delegates bulk work to lower-cost workers. See [Optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence) for both strategies, measured examples, and implementation options.
9494
9595## Next steps
9696
about-claude/models/optimizing-for-cost-and-intelligence Changed · +32 / -60 lines
from line 1
11---
22title: Optimizing for cost and intelligence
33url: https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence
4description: Balance cost and intelligence on the Claude Platform, with measured results for prompt caching, effort, model choice, output caps, and multi-model strategies.
4description: Balance cost and intelligence on the Claude Platform, with measured results for prompt caching, effort, model choice, output caps, and multimodel strategies.
55---
66
77The most capable model can be too expensive at scale, and the least expensive model can fall short on quality. The Claude Platform gives you direct control over that tradeoff. You choose the model, the effort level, and the architecture for each request, which lets you place a workload almost anywhere on the cost-to-intelligence frontier.
from line 14
1414
1515The levers come in two kinds:
1616
17* **Free wins** cut spend without touching quality: prompt caching, token hygiene, a prompt audit against the model you are running, [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) at 50% off for work that can wait up to 24 hours, and [workspace spend limits](https://platform.claude.com/docs/en/api/rate-limits#setting-lower-limits-for-workspaces) as the backstop.
18* **Tradeoffs** exchange cost for intelligence: model choice, effort, output caps and session budgets, an elapsed-time clock, and multi-model architectures.
17* **Free wins** cut spend without touching quality: prompt caching, token hygiene, a prompt audit against the model you are running, and [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing) at 50% off for work that can wait up to 24 hours.
18* **Tradeoffs** exchange cost for intelligence: model choice, effort, output caps and session budgets, an elapsed-time clock, and multimodel architectures.
1919
20Each lever comes with measured results and the rule for when it pays. In Anthropic’s measurements, prompt caching was usually the largest lever. The multi-model levers are narrower; a second model was measured in two shapes, an advisor and an orchestrator.
20A [workspace spend limit](https://platform.claude.com/docs/en/api/rate-limits#setting-lower-limits-for-workspaces) is the backstop for both kinds of lever: see [Set budgets and output caps](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#set-budgets-and-output-caps).
2121
22Each lever comes with measured results and the rule for when it pays. In Anthropic’s measurements, prompt caching was usually the largest lever. The multimodel levers are narrower; a second model was measured in two shapes, an advisor and an orchestrator.
23
2224## Start here
2325
2426Match your situation to a row.
from line 100
98100
99101Anthropic measured a small agent that triages bug reports ([Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens)) with pauses inserted before some turns to simulate a person’s delay<sup>[16](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. Accuracy stayed within run-to-run noise at every setting measured. Anthropic also measured extra requests that keep the 5-minute cache warm (keep-alive requests).
100102
101To decide, count the gaps between consecutive requests in a conversation, and find your row in the following table:
103To decide, count the gaps between consecutive requests in a conversation, and find your row in the following table. A row that names your model takes precedence over a row with “Any” in the Model column:
102104
103105| Your gaps between requests | Model | Use |
104106| ---------------------------------------------------------------------------------------------------------- | ------------------------------------- | -------------------------------------------------------- |
from line 108
106108| About 1 gap in 20 or more falls between 5 minutes and an hour, and few gaps run over an hour | Any | 1-hour duration |
107109| Gaps over an hour are common: about 60% or more of your pauses longer than 5 minutes also run past an hour | Any | 5-minute default |
108110| Only 1 or 2 gaps in 20 fall between 5 minutes and an hour, and none lasts more than about half an hour | Claude Opus 5.5 and Claude Sonnet 5.5 | 5-minute cache kept warm, instead of the 1-hour duration |
109| A pause comes before every turn | Claude Opus 5.5 and Claude Sonnet 5.5 | 1-hour duration |
111| A pause of more than 5 minutes comes before every turn, and few pauses run over an hour | Claude Opus 5.5 and Claude Sonnet 5.5 | 1-hour duration |
110112| Pauses run for minutes | Claude Fable 5.1 and Claude Fable 5.2 | 5-minute cache kept warm, instead of the 1-hour duration |
111| Pauses run toward an hour | Claude Fable 5.1 and Claude Fable 5.2 | 1-hour duration |
113| Pauses run toward an hour, and few run over an hour | Claude Fable 5.1 and Claude Fable 5.2 | 1-hour duration |
112114
113115On Claude Haiku 5.5, use the “Any” rows: it reads the cache at the standard 0.1x the input price, twice the 0.05x of Claude Opus 5.5 and Claude Sonnet 5.5, so by list prices each keep-alive request costs twice as much, relative to the input price, as on those two models. A `max_tokens: 0` request refreshed its cache in a separate test (reference 16).
114116
from line 192
190192
191193#### What breaks the cache
192194
193Keep per-request text in the newest user turn, after the last cache breakpoint, and make every cache-invalidating change at a natural break, such as the first request after a compaction. The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it.
195Put per-request text, such as a status line, at the end of the newest user turn, after the last cache breakpoint. On later requests, leave each earlier turn as you sent it, with its old status line still in it. Make cache-invalidating changes at a natural break, such as the first request after a compaction. On models that run the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), a request that edits the system prompt or `tools` can get a 400 error even at such a break. Send those changes in `messages` instead, where your platform supports it (see [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits)). The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it.
194196
195When something must change mid-conversation, send it in the form that keeps the cache, where the model supports it. In Anthropic’s test on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, on a cached conversation of about 100,000 tokens, editing the system prompt cost about 25 to 50 times what the same text cost as a mid-conversation system message. Changing effort at the top level cost 20 to 40 times what it cost per message<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>:
197When something must change mid-conversation, send it in the form that keeps the cache, where the model supports it. Anthropic tested each change both ways on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, on a cached conversation of about 100,000 tokens that held the model’s first reply with its thinking. Editing the system prompt cost about 25 to 50 times what the same text cost as a mid-conversation system message. Changing effort at the top level cost 20 to 40 times what changing it in a message cost<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>:
196198
197199<Frame>
198200 
199201</Frame>
200202
201At list prices, the stakes are highest on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, where a break rewrites the prefix at 1.25x the input price instead of reading it at 0.025x. On Claude Haiku 5.5, a system prompt edit cost 12.5x as much as an unchanged request, because the edit rewrote the whole conversation. On models that run the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), a request that makes this edit and sends earlier thinking blocks back can get a 400 error instead<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. On Claude Fable 5.2 and Claude Mythos 5.2, every account gets the 400 error by default, including accounts created before August 31, 2026. The top-level effort change, in a conversation that held the model’s first reply with its thinking, rewrote all but the system prompt. These figures are from the Messages API.
203When a change invalidates the cache, the part of the prefix it affects is written again instead of read. A write to the 5-minute cache costs 1.25x the input price, and a cache read costs a small fraction of the input price. At list prices, that write costs 50 times a read on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, where a cache read costs 0.025x the input price. That write costs 25 times a read on Claude Opus 5.5 and Claude Sonnet 5.5 (0.05x), and 12.5 times on Claude Haiku 5.5 (0.1x). The chart’s figures are from the Messages API.
202204
205A request that edits the system prompt or `tools` can also fail outright. On models that run the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), a request that makes either edit and sends earlier thinking blocks back can get a 400 error<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. In a separate Anthropic test, waiting for a compaction didn’t avoid the error: on Claude Opus 5.5 and Claude Fable 5.2, such a request still got it as the first request after a compaction at a token threshold<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. By default on the Claude API, a request that fails the check gets the error on every account if the model is Claude Fable 5.2, Claude Mythos 5.2, or Claude Mythos 5.1. If the model is Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, or Claude Haiku 5.5, the request gets the error on some accounts and no error on others. For the outcomes by model and account, see [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement).
206
203207**What to do.**
204208
205209* Put nothing that changes per request, such as a timestamp or a queue position, ahead of the stable prefix: it turns every request into a full cache write. In Anthropic’s test, a 25-token status line at the front of the system prompt made each request write the whole conversation; moved to the end of the newest user turn, it left the cache read intact<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>.
206210* The [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#what-invalidates-the-cache) page lists the changes that invalidate the cache, such as a change to [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort), the thinking configuration, the [`speed`](https://platform.claude.com/docs/en/build-with-claude/fast-mode) setting, the system prompt, or a tool definition. Changing the output format invalidates the cache for that conversation (see [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#prompt-modification-and-token-costs)).
207* Check which models support each form: [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), and [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation), which is in beta.
211* Check which models support each form: [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), and [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort-per-message), which is in beta.
208212* After a cache-invalidating change, confirm cache reads have not dropped; if they have, [cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) shows where the prefix diverged.
209213
210On an earlier model, Anthropic measured when to make such a change, on the triage agent’s long sessions<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. An effort change and an added tool cost more mid-session, or on the request that triggered the compaction, than on the first request after compaction. Accuracy was within run-to-run noise. The sessions with no changes cost more than those changed after compaction for another reason: they ran at the default effort throughout, and two of them compacted a second time, while the others started at low effort:
214On an earlier model, Anthropic measured when to make such a change, on long sessions of the issue-triage agent described in [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens)<sup>[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. The sessions that made changes started at low effort, then switched to the default effort and added one tool. Making the two changes mid-session cost the most. Making them on the request that triggered the compaction cost nearly as much, because that request still carried the whole conversation and wrote it to the cache again. Making them on the next request, the first after the compaction, cost the least. Accuracy was within run-to-run noise. That model doesn’t run the prefix check. On a model that does, add the tool in a message instead: see [Add or remove tools with `tool_addition` and `tool_removal`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#tool-changes), which is in beta. The following chart also shows sessions with no changes. They aren’t a like-for-like baseline, because they ran at the default effort throughout and two of them compacted a second time:
211215
212216<Frame>
213217 
from line 271
267271
268272Anthropic measured these levers on an earlier model<sup>[28](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>:
269273
274* In these runs, the prune was a short function in the issue-triage agent’s own code: at each task boundary, it replaced each search result of over 2,000 characters with a one-line extract.
270275* On the 20-issue run the levers saved little or nothing, and context editing made the run cost more.
271276* On the long run the prune and compaction both cut the cost, while context editing changed nothing.
272* The prune is a few lines you write yourself: at each task boundary, replace large stale tool results with a one-line extract.
273* The prune caches well because the edits sit at the tail of the conversation, where the next task adds new content anyway.
274* Run-wide, the prune and context editing cache about equally well. If you use context editing, [clear in a few large batches](https://platform.claude.com/docs/en/build-with-claude/context-editing#context-editing-and-prompt-caching).
277* If you use context editing, [clear in a few large batches](https://platform.claude.com/docs/en/build-with-claude/context-editing#context-editing-and-prompt-caching), because each clear costs a cache write.
275278
276279<Note>
277 On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, rewriting an earlier tool result [invalidates every thinking block after it](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), so use compaction instead. The prune was measured on an earlier model without [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking); on these models, [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) and [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) run on the server and don’t invalidate thinking blocks. [Send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned): dropping their thinking blocks costs output tokens on every turn, because Claude [re-creates the reasoning](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#drop-block-cost).
280 Don’t use the prune on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, or Claude Haiku 5.5. On these models, if your application rewrites an earlier tool result, that invalidates every thinking block already in the history after the result (see [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check)), and the request might fail (see [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement)). The prune was measured on an earlier model without [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking). Use [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) instead: in the same test, it also cut the cost of the long run. Compaction and [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) both run on the server, so neither invalidates thinking blocks. [Send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned): dropping their thinking blocks costs output tokens on every turn, because Claude [re-creates the reasoning](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#drop-block-cost).
278281</Note>
279282
280The prune, adapted from the triage agent’s code:
281
282```python
283import re
284
285PRUNED = "[pruned at issue boundary]"
286
287
288def prune_task_boundary(messages, tool_name_by_id, threshold=2000):
289 """Call once per task boundary. Replaces large, stale search results with a one-line extract."""
290 for message in messages:
291 if message["role"] != "user" or not isinstance(message["content"], list):
292 continue
293 for block in message["content"]:
294 if not (isinstance(block, dict) and block.get("type") == "tool_result"):
295 continue
296 if tool_name_by_id.get(block.get("tool_use_id")) != "search_issues":
297 continue
298 result_text = block.get("content")
299 if not isinstance(result_text, str) or len(result_text) <= threshold:
300 continue
301 if result_text.startswith(PRUNED):
302 continue # already pruned on an earlier boundary
303 # cap single-line results so the extract stays short
304 first_line = result_text.split("\n", 1)[0].strip()[:200]
305 refs = re.findall(r"#(\d+)", result_text)[:5]
306 extract = f"{PRUNED} {first_line}"
307 if refs:
308 extract += " kept refs: " + " ".join("#" + r for r in refs)
309 block["content"] = extract
310```
311
312283### Batch work that can wait
313284
314285Route every request no one is waiting on through the [Batch API](https://platform.claude.com/docs/en/build-with-claude/batch-processing), and keep the interactive path for the rest. The Batch API takes 50% off every token of a request, including cached ones, in exchange for results arriving any time within 24 hours.
from line 396
425396 
426397</Frame>
427398
428The [multi-model strategies](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#combine-models) exist to spend frontier intelligence on that tail without paying frontier rates for the rest.
399The [multimodel strategies](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#combine-models) exist to spend frontier intelligence on that tail without paying frontier rates for the rest.
429400
430401### Upgrade the model
431402
from line 453
482453
483454**What to do.**
484455
485* Sweep two or three effort levels on a sample of your own traffic, each in a separate session: changing top-level effort mid-session [invalidates the cache](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#cache-repeated-context) and distorts the comparison. The curve is the baseline any multi-model strategy must beat ([step 2 of measuring on your own workload](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#measure-on-your-own-workload)).
456* Sweep two or three effort levels on a sample of your own traffic, each in a separate session: changing top-level effort mid-session [invalidates the cache](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#cache-repeated-context) and distorts the comparison. The curve is the baseline any multimodel strategy must beat ([step 2 of measuring on your own workload](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#measure-on-your-own-workload)).
486457* On long-horizon coding, effort is a real tradeoff, which [re-running failures at higher effort](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#re-run-failures-at-higher-effort) turns back into a saving. At `medium`, Claude Sonnet 5.5 scored about 7 points lower than at its default, `high`, on the SWE-bench Pro<sup>[3](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup> subset for about 59% of the cost per task (2 runs each), and scored 62.7% compared with 77.8% on the internal agentic-coding benchmark<sup>[11](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup> (1 attempt per task).
487458* At `xhigh` and `max`, Claude Sonnet 5.5 can start its own rounds of review after it finishes a task, which takes more time and tokens. To keep that work on the task, add the prompt under “Thoroughness at `xhigh` and `max` effort” in [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#steer-initiative-and-scope) to your system prompt.
488459* On research tasks, measure the model you ship. Claude Fable 5.2 scored 3.3 points higher at `high` than at `low` on DeepResearch Bench II, for 3.2 times the cost, and not measurably higher at `medium` than at `low`; Claude Opus 5.5 scored 13.3 points lower at `low` than at `medium` on DRACO<sup>[21](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>. The two results come from different models on different benchmarks, so they show that the answer varies, not why.
from line 536
565536
566537On HLE<sup>[22](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup> and an internal physics set<sup>[23](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs)</sup>, the typical task took 14% and 7% less time, and the physics score was 3.0 points lower. Lowering effort to `low` saved more time and cost than the changes did, and lost more score (reference 21). Check the score on your own tasks before you adopt the changes.
567538
568For working code, see the Claude Cookbook recipe [Multi-agent teams under latency pressure and budgets](https://github.com/anthropics/claude-cookbooks/blob/main/patterns/agents/latency_multi_agent.ipynb), which applies both changes to a team of agents. To say that time matters in the system prompt instead, see [Time signals for multiagent harnesses](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#time-signals-for-multi-agent-harnesses).
539Reference 21 gives the exact text used for both changes in the measured runs. For working code, see the Claude Cookbook recipe [Multi-agent teams under latency pressure and budgets](https://github.com/anthropics/claude-cookbooks/blob/main/patterns/agents/latency_multi_agent.ipynb), which applies both changes to a team of agents. To use the system prompt instead of the first `user` message to say that time matters, see [Time signals for multiagent harnesses](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#time-signals-for-multi-agent-harnesses).
569540
570541The following chart also plots a team, whose lead agent rarely started helpers, and a single agent at `low` effort:
571542
from line 628
657628Measure on your own workload: the numbers on this page reflect list prices at the time of measurement and will drift as models and prices change, and your escalation rate, how cleanly tasks split, and transcript length move them too. The method stays the same:
658629
6596301. Pull a few tasks from production logs, weighted like real traffic, and [write outcome checks](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) for each: tests pass, ticket closed, row count correct. Record cost per task beside the score.
6602. Baseline the model tiers across effort levels, not only the default, and plot score against spend. A multi-model configuration must beat the single model’s whole curve.
6613. If the curve shows a gap effort can’t close, add the multi-model strategy that fits and re-run the suite.
6312. Baseline the model tiers across effort levels, not only the default, and plot score against spend. A multimodel configuration must beat the single model’s whole curve.
6323. If the curve shows a gap effort can’t close, add the multimodel strategy that fits and re-run the suite.
6626334. Run the winner in shadow on a traffic slice before cutover, then keep the suite running.
663634
664635**How to price a task.** Price each of the five token counts in a response’s `usage` at its own rate: uncached input, 5-minute and 1-hour cache writes at 1.25x and 2x the input price, cache reads, and output. Sum them across the task’s requests (the [Usage and Cost Analytics API](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api) reports the aggregate). On Claude Haiku 5.5, use the rates for each request’s prompt length, counting cache reads and writes (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)). When `usage.speed` is `"fast"`, use the [fast mode rates](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing).
from line 638
667638
668639<CodeGroup exclude="shell:cURL, shell:CLI">
669640 <CodeGroupItem language="cURL">
670 This calculation needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
641 This calculation needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
671642 </CodeGroupItem>
672643
673644 <CodeGroupItem language="CLI">
674 This calculation needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
645 This calculation needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
675646 </CodeGroupItem>
676647
677648 ```python Python
from line 783
812783
813784 $client = new Client();
814785 $response = $client->messages->create(
815 model: 'claude-opus-5-5',
786 model: Model::CLAUDE_OPUS_5_5,
816787 maxTokens: 1024,
817788 messages: [['role' => 'user', 'content' => 'Hello, Claude']],
818789 );
from line 841
870841| Lower effort | On long coding tasks, `medium` cost about 30% to 52% less than `high`, and `low` about two thirds less | Up to 34 points lower, depending on the task and the model; 3.3 on one research agent | Faster | [Tune effort](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#tune-effort) |
871842| Re-run failures | About 40% less than running everything at `high`, at the same pass rate or slightly better | None | A second attempt on the tasks that fail | [Re-run failures at higher effort](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#re-run-failures-at-higher-effort) |
872843| Ask for shorter answers | About 13% less, from 39% fewer output tokens | None | Faster | [Set budgets and output caps](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#set-budgets-and-output-caps) |
873| Raising `max_tokens` | None: cost per solved task did not rise at 64,000 | A gain: up to 57 points more tasks solved at 64,000 on one coding benchmark; none on another | Neutral | [Set budgets and output caps](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#set-budgets-and-output-caps) |
844| Raise `max_tokens` | None: cost per solved task did not rise at 64,000 | A gain: up to 57 points more tasks solved at 64,000 on one coding benchmark; none on another | Neutral | [Set budgets and output caps](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#set-budgets-and-output-caps) |
874845| Advisor | None: about 2.1 times the cost of the model alone, on a coding benchmark | On coding, a small gain that may be chance; on chart reading, a loss | About 1.4 extra calls per attempt, on coding | [Advisor strategy](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#advisor-strategy-escalate-hard-decisions) |
875846| Orchestrator | With subagents on the next model down, about a third less than the orchestrator’s model alone at its default effort, on work larger than one context window; on routine work, measure first | No measurable loss on that work | Up to 25 subagents at a time | [Orchestrator strategy](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#orchestrator-strategy-delegate-bulk-work) |
876847| Fast mode | None: twice the standard token prices | None | Up to 2.5x higher output tokens per second | [Show the model elapsed time](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#show-the-model-elapsed-time) |
from line 1012
10411012 * **October 2026 test, one change to a long conversation:** Measured October 20, 2026, on Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, on the Messages API with no tools, adaptive thinking, each model’s default effort, the 5-minute cache, a cache breakpoint on the system prompt, and [automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching). The conversation held about 101,000 tokens: a 20,000-token system prompt, 13 user turns of filler text, the model’s own reply to the first turn with its thinking block, and one-word replies to the rest. Once one request had cached the conversation, a second added one short turn, and each measured request sent that longer conversation with one change. Two conversations per model gave the same result.
10421013 * **October 2026 test, tokens read and written:** With no change, and with a per-message effort change, the request read all 101,000 tokens and wrote none. With a 25-token mid-conversation system message, or a 25-token status line at the end of the newest user turn, it read them all and wrote only the new text. A top-level effort change (to `low` on Claude Fable 5.1 and Claude Sonnet 5.5, to `high` on Claude Opus 5.5 and Claude Haiku 5.5) read the 20,000-token system prompt and wrote 81,000 tokens. The same 25 tokens at the front or the end of the system prompt read nothing and wrote all 101,000. The request after a mid-conversation system message, a top-level effort change, or 25 tokens added to the end of the system prompt read the new prefix; a new status line at the front wrote everything again. A further test on October 21, 2026, on the same four models with conversations of 5,000 tokens, and on all but Claude Fable 5.1 with conversations of 100,000 tokens, all with one-word replies, sent a beta header for the first time mid-conversation, as a first per-message effort change may: that request read everything the request before it had cached, all 54 times. A system message sent with no beta header did the same, all 15 times.
10431014 * **October 2026 test, how priced:** The chart gives the prompt side of one request, from its `usage` fields at list prices. The chart’s values, in the order system prompt edit, system message, top-level effort change, and per-message effort change: Claude Fable 5.1 $1.26 USD, $0.026 USD, $1.02 USD, and $0.025 USD; Claude Opus 5.5 $0.50 USD, $0.020 USD, $0.41 USD, and $0.020 USD; Claude Sonnet 5.5 $0.25 USD, $0.010 USD, $0.20 USD, and $0.010 USD. The unchanged request repeated an earlier request byte for byte; a new turn of about 25 tokens adds under $0.001 USD. On Claude Haiku 5.5, whose requests were over 100,000 prompt tokens and so at its [long context prices](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing): $0.063 USD for the system prompt edit, $0.052 USD for the effort change, and $0.005 USD for the read. The requests ran on an Anthropic-internal organization whose usage is metered the same way as a customer organization’s. For that organization, the API lets failing thinking blocks through when a request leaves `prefix_mismatch_behavior` unset, so the system prompt edits in these tests were accepted. On an account created on or after August 31, 2026, 00:00 UTC, the same edit gets a 400 error on all four models, because each request sends an earlier thinking block back.
1015 * **November 2026 test, edits after a compaction:** Run November 9, 2026, on Claude Opus 5.5 and Claude Fable 5.2, on the Messages API with adaptive thinking, `high` effort, no caching, one tool defined, `tool_choice` set to `none`, [`prefix_mismatch_behavior`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) set to `"error"`, and [compaction at a token threshold](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) with a trigger of 50,000 tokens. A first request of about 55,700 tokens triggered a compaction, and its reply held a compaction block followed by a thinking block. The next request sent that reply back with one new user turn. Unchanged, it succeeded. With one tool added to `tools`, or with the system prompt reworded, it got the 400 error. In a conversation with no compaction, the same two edits got the 400 error, and so did removing a text block from an earlier user turn. One conversation of each kind per model. On Claude Fable 5.2, the first large conversation’s reply held no thinking block. A second conversation replaced the first, with a harder question, a higher `max_tokens`, and custom compaction `instructions`, and only the second counts. The requests ran on the Claude API.
10441016 * **What was measured:** The triage agent’s long variant from [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens), run August 24, 2026, on Claude Sonnet 5 with the 5-minute cache, cost from the usage fields at list prices, five sessions per arm: a no-change arm at the default effort throughout ($0.81 USD per session), and two arms that start at low effort and make the same two cache-breaking changes, a switch to the default effort and one added tool, either mid-session at requests 12 and 17 ($0.95 USD) or together on the first request after the first compaction ($0.75 USD).
10451017 * **Fourth arm:** A fourth arm of six sessions, run August 25, 2026, made the same two changes on the request that triggered the first compaction ($0.92 USD per session): that request’s summarization pass wrote the 81,000-token context to the cache instead of reading it, so that pass cost $0.21 USD against $0.04 USD for the same pass in the boundary arm.
10461018 * **Compaction:** Sessions first compacted at request 21 to 25 (16 of the 21 sessions at request 22), once the prompt passed the 80,000-token compaction trigger, and two no-change sessions compacted a second time near the end. The boundary arm’s lower total than the no-change arm reflects its low-effort requests before the change and those second compactions rather than caching: the two arms’ re-write costs differ by under $0.01 USD.
from line 1070
10981070
1099107125. **Claude Managed Agents task set:**
11001072
1101 * **What was measured:** An Anthropic-internal set of 79 scripted agent tasks in eight areas, including memory, multi-agent, and long-context work, run as [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) sessions in which the test answers every tool call. Each task ran five times per model.
1073 * **What was measured:** An Anthropic-internal set of 79 scripted agent tasks in eight areas, including memory, multiagent, and long-context work, run as [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) sessions in which the test answers every tool call. Each task ran five times per model.
11021074 * **Runs:** The figures are from one run per model on October 7, 2026, graded that day. In three more runs of the same tasks on October 8 and 9, 2026, Claude Haiku 5.5 passed 91% to 93% of attempts, and in one more run on October 8, Claude Haiku 4.5 passed 63%.
11031075 * **How scored:** An attempt passed only if the grader, Claude Sonnet 4.6, grading once, marked every line of the task’s checklist as met, so pass rates depend on the grader. On all but one task, a separate call, shown the tool results in full, graded the line that checks the files and messages the agent wrote through its tools against those results.
11041076 * **How priced:** Costs are token costs at list prices with 5-minute prompt caching, priced request by request, and exclude session runtime.
about-claude/pricing Changed · +69 / -50 lines
from line 6
66
77This page provides detailed pricing information for Anthropic’s models and features. All prices are in USD.
88
9For the most current pricing information, visit [claude.com/pricing](https://claude.com/pricing).
9For the most current pricing information, see the [Claude pricing](https://claude.com/pricing) page.
1010
1111## Model pricing
1212
from line 77
7777
7878 For implementation details and code examples:
7979
80 * [Amazon Bedrock global versus regional endpoints](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#regions) for Opus 4.7, Haiku 4.5, and later models, or the [legacy integration](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#global-vs-regional-endpoints) for all other models on Bedrock
81 * [Claude Models on Google Cloud (Google managed) global, multi-region, and regional endpoints](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#global-multi-region-and-regional-endpoints)
80 * Amazon Bedrock global versus regional endpoints: [Claude in Amazon Bedrock (`bedrock-mantle`)](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#regions) or [Claude on Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#global-vs-regional-endpoints), depending on whether you call `bedrock-mantle` or `bedrock-runtime`
81 * Google Cloud global, multi-region, and regional endpoints: [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed#global-multi-region-and-regional-endpoints)
8282</Note>
8383
8484## Claude Platform on AWS pricing
from line 85
8585
8686[Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) bills through AWS Marketplace using Claude Consumption Units (CCUs). Anthropic rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at $0.01 USD per CCU, and reports the CCU quantity to AWS Marketplace hourly. Your AWS bill shows a single CCU line item.
8787
88| Concept | Details |
89| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
90| **Billing unit** | Claude Consumption Unit (CCU) |
91| **CCU price** | $0.01 USD per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
92| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Claude API pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing)), then converted to CCUs at $0.01 USD per CCU |
93| **Billing cadence** | Hourly metering to AWS Marketplace; monthly invoices |
94| **Payment model** | Arrears only (postpaid); no prepaid credits |
95| **Discounts** | Applied as fewer CCUs metered |
96| **Tax** | Pre-tax metering; AWS Marketplace handles tax |
97| **Cost visibility** | Real-time breakdown in the Claude Console (access through the AWS Console); AWS Cost Explorer shows aggregated CCU |
88| Concept | Details |
89| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
90| **Billing unit** | Claude Consumption Unit (CCU) |
91| **CCU price** | $0.01 USD per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
92| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing)), then converted to CCUs at $0.01 USD per CCU |
93| **Billing cadence** | Hourly metering to AWS Marketplace; monthly invoices |
94| **Payment model** | Arrears only (postpaid); no prepaid credits |
95| **Discounts** | Applied as fewer CCUs metered |
96| **Tax** | Pre-tax metering; AWS Marketplace handles tax |
97| **Cost visibility** | Real-time breakdown in the Claude Console (access through the AWS Console); AWS Cost Explorer shows aggregated CCU |
9898
99**CCU:** Claude Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (e.g., Claude Platform on AWS), usage will be invoiced in Claude Consumption Units (“CCU”) rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices on [claude.com/pricing#api](https://claude.com/pricing#api), after application of any discounts.
99**CCU:** Claude Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (for example, Claude Platform on AWS), usage is invoiced in Claude Consumption Units (“CCU”) rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices in the [API section of the Claude pricing page](https://claude.com/pricing#api), after application of any discounts.
100100
101101### Inference geography
102102
from line 114
114114
115115[Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) bills through the Azure Marketplace using Claude Consumption Units (CCUs). Anthropic rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at $0.01 USD per CCU, and reports the CCU quantity to the Azure Marketplace hourly. Your Azure bill shows a single CCU line item.
116116
117| Concept | Details |
118| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
119| **Billing unit** | Claude Consumption Unit (CCU) |
120| **CCU price** | $0.01 USD per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
121| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Claude API pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing)), then converted to CCUs at $0.01 USD per CCU |
122| **Billing cadence** | Hourly metering to the Azure Marketplace; monthly invoices |
123| **Payment model** | Arrears only (postpaid); no prepaid credits |
124| **Discounts** | Applied as fewer CCUs metered |
125| **Tax** | Pre-tax metering; Azure Marketplace handles tax |
126| **Cost visibility** | Azure Cost Management shows aggregated CCU |
117| Concept | Details |
118| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
119| **Billing unit** | Claude Consumption Unit (CCU) |
120| **CCU price** | $0.01 USD per CCU (fixed; discounts apply at token-to-CCU conversion, not to the CCU price) |
121| **Conversion** | Token usage rated in USD at standard per-model, per-feature rates (same as [Model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing)), then converted to CCUs at $0.01 USD per CCU |
122| **Billing cadence** | Hourly metering to the Azure Marketplace; monthly invoices |
123| **Payment model** | Arrears only (postpaid); no prepaid credits |
124| **Discounts** | Applied as fewer CCUs metered |
125| **Tax** | Pre-tax metering; Azure Marketplace handles tax |
126| **Cost visibility** | Azure Cost Management shows aggregated CCU |
127127
128**CCU:** Claude Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (e.g., Claude Platform on AWS, Claude in Microsoft Foundry), usage will be invoiced in Claude Consumption Units (“CCU”) rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices on [claude.com/pricing#api](https://claude.com/pricing#api), after application of any discounts.
128**CCU:** Claude Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (for example, Claude Platform on AWS, Claude in Microsoft Foundry), usage is invoiced in Claude Consumption Units (“CCU”) rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices in the [API section of the Claude pricing page](https://claude.com/pricing#api), after application of any discounts.
129129
130130### Inference geography
131131
from line 144
144144
145145Prompt caching uses the following pricing multipliers relative to base input token rates:
146146
147| Cache operation | Multiplier | Duration |
148| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------ |
149| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
150| 1-hour cache write | 2x base input price | Cache valid for 1 hour |
151| Cache read (hit) | 0.1x base input price (0.025x on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1; 0.05x on Claude Opus 5.5 and Claude Sonnet 5.5) | Same duration as the preceding write |
147| Cache operation | Multiplier | Duration |
148| -------------------- | ------------------------------------ | ------------------------------------ |
149| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
150| 1-hour cache write | 2x base input price | Cache valid for 1 hour |
151| Cache read (hit) | 0.1x base input price on most models | Same duration as the preceding write |
152152
153Cache write tokens are charged when content is first stored. Cache read tokens are charged when a subsequent request retrieves the cached content. A cache hit costs 10 percent of the standard input price, which means caching pays off after one cache read for the 5-minute duration (1.25x write), or after two cache reads for the 1-hour duration (2x write). On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, a cache hit costs 2.5 percent of the standard input price ($0.20 USD per million tokens on Claude Fable 5.2 and Claude Mythos 5.2, $0.25 USD on Claude Fable 5.1 and Claude Mythos 5.1). On Claude Opus 5.5 and Claude Sonnet 5.5, a cache hit costs 5 percent of the standard input price ($0.20 USD per million tokens on Claude Opus 5.5, $0.10 USD on Claude Sonnet 5.5).
153Cache write tokens are charged when content is first stored. Cache read tokens are charged when a subsequent request retrieves the cached content.
154154
155Caching saves money after a small number of cache reads:
156
157* **5-minute duration (1.25x write):** after one cache read
158* **1-hour duration (2x write):** after two cache reads
159
160What a cache hit costs depends on the model:
161
162| Model | Cache hit multiplier | Cache hit price per million tokens |
163| -------------------------------------- | -------------------- | ------------------------------------------------------------------------------------------- |
164| Claude Fable 5.2 and Claude Mythos 5.2 | 0.025x | $0.20 USD |
165| Claude Fable 5.1 and Claude Mythos 5.1 | 0.025x | $0.25 USD |
166| Claude Opus 5.5 | 0.05x | $0.20 USD |
167| Claude Sonnet 5.5 | 0.05x | $0.10 USD |
168| All other models | 0.1x | See [Model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing) |
169
155170These multipliers stack with other pricing modifiers, including the Batch API discount and data residency.
156171
157172For implementation details, supported models, and code examples, see [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching).
from line 175
160175
161176For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. On Claude Haiku 5.5, the multiplier also applies to the higher prices for prompts over 100,000 tokens (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)). Global routing (the default) uses standard pricing.
162177
163This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments that use the US Data Zone Standard deployment type (see [Inference geography](https://platform.claude.com/docs/en/about-claude/pricing#foundry-inference-geography)). Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Bedrock, have independent regional pricing. See [Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) and [Google Cloud pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models) for details. Earlier models do not support the `inference_geo` parameter and always use standard pricing; requests that include the parameter on these models return a 400 error.
178This applies to the Claude API (first-party), Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed). On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments that use the US Data Zone Standard deployment type (see [Inference geography](https://platform.claude.com/docs/en/about-claude/pricing#foundry-inference-geography)). Partner-operated platforms, Claude Models on Google Cloud (Google managed) and Amazon Bedrock, have independent regional pricing. See [Amazon Bedrock pricing](https://aws.amazon.com/bedrock/pricing/) and [Google Cloud pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models) for details. Earlier models do not support the `inference_geo` parameter and always use standard pricing; requests that include the parameter on these models return a 400 error.
164179
165180For more information, see [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency).
166181
167182### Fast mode pricing
168183
169[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) provides significantly faster output for Claude Fable 5.2, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 at premium pricing. Fast mode for Claude Opus 5 and Claude Opus 4.8 is in research preview. Fast mode pricing applies across the full context window, including requests over 200k input tokens. Fast mode is available on the Claude API (first-party). For Claude Opus 5.5, it is also available on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#billing) and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure.
184[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) provides up to 2.5x higher output tokens per second at premium pricing. It is available for Claude Fable 5.2, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8. Fast mode is in research preview for Claude Opus 5 and deprecated for Claude Opus 4.8.
170185
186Fast mode pricing applies across the full context window, including requests over 200k input tokens.
187
188Fast mode is available on the Claude API (first-party). For Claude Opus 5.5, it is also available on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#billing) and on [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) for deployments hosted on Azure.
189
171190Fast mode for Claude Fable 5.2 is also available on [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed#billing).
172191
173192Fast mode for Claude Fable 5.2 is also available on [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). Google Cloud sets its prices there. See [Cloud platform pricing](https://platform.claude.com/docs/en/about-claude/pricing#cloud-platform-pricing).
from line 296
277296
278297For current per-model prices, refer to the [model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing) section.
279298
280For more information about tool use implementation and best practices, see [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
299For more information about tool use implementation and best practices, see [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview).
281300
282301### Specific tool pricing
283302
from line 407
388407
389408#### Computer use tool
390409
391Computer use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:
410Computer use follows the standard [tool use pricing in the tool use overview](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:
392411
393**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
412**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request: about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models. These tokens cover the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The response `usage` reports the exact count for a request, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
394413
395414**Earlier tool versions:** The following figures apply to the `computer_20251124` and `computer_20250124` tool versions, not to `computer_toolset_20260801`:
396415
397416* System prompt overhead: 466–499 tokens added to the system prompt
398* Tool definition: about 735 input tokens per tool definition (measured with `computer_20250124`)
417* Tool definition: about 735 input tokens for each tool definition (measured with `computer_20250124`)
399418
400419**Additional token consumption:**
401420
402* Screenshot and zoom images returned in tool results, billed as image input (see [Vision pricing](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
421* Screenshot and zoom images returned in tool results, billed as image input (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
403422* Tool execution results returned to Claude
404423
405424<Note>
from line 427
408427
409428#### Browser use tool
410429
411Browser use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:
430Browser use follows the standard [tool use pricing in the tool use overview](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:
412431
413**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
432**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request: about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models. These tokens cover the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The response `usage` reports the exact count for a request, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
414433
415434**Additional token consumption:**
416435
417* Screenshot and zoom images returned in tool results, billed as image input (see [Vision pricing](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
436* Screenshot and zoom images returned in tool results, billed as image input (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
418437* Text tool results returned to Claude, such as accessibility trees, page text, and console or network entries
419438
420439<Note>
from line 522
503522Volume discounts might be available for high-volume users. These are negotiated on a case-by-case basis.
504523
505524* Standard usage tiers use the pricing shown in [Model pricing](https://platform.claude.com/docs/en/about-claude/pricing#model-pricing).
506* Enterprise customers can [contact sales](mailto:[email protected]) for custom pricing.
525* Enterprise customers can [email sales](mailto:[email protected]) for custom pricing.
507526* Academic and research discounts might be available.
508527
509528### Enterprise pricing
from line 534
515534* Dedicated support
516535* Custom terms
517536
518Contact the sales team at [[email protected]](mailto:[email protected]) or through the [Claude Console](https://platform.claude.com/usage/limits) to discuss enterprise pricing options.
537To discuss enterprise pricing options, email [[email protected]](mailto:[email protected]) or [contact sales from the Claude Console](https://platform.claude.com/usage/limits).
519538
520539## Billing and payment
521540
from line 541
522541* Billing is based on actual monthly usage.
523542* All payments are in USD.
524543* Credit card and invoicing options are available.
525* Usage tracking is available in the Claude Console at [platform.claude.com](https://platform.claude.com/).
544* Usage tracking is available in the [Claude Console](https://platform.claude.com/).
526545
527546## Frequently asked questions
528547
from line 551
532551
533552### Are there free tiers or trials?
534553
535New users receive a small amount of free credits to test the API. [Contact sales](mailto:[email protected]) for information about extended trials for enterprise evaluation.
554New users receive free credits to test the API. [Email sales](mailto:[email protected]) for information about extended trials for enterprise evaluation.
536555
537556### How do discounts stack?
538557
about-claude/use-case-guides/legal-summarization Changed · +4 / -4 lines
from line 477
477477
478478<CodeGroup exclude="shell">
479479 <CodeGroupItem language="cURL">
480 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
480 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
481481 </CodeGroupItem>
482482
483483 <CodeGroupItem language="CLI">
484 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
484 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
485485 </CodeGroupItem>
486486
487487 ```python Python
from line 891
891891
892892<CodeGroup exclude="shell">
893893 <CodeGroupItem language="cURL">
894 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
894 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
895895 </CodeGroupItem>
896896
897897 <CodeGroupItem language="CLI">
898 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
898 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
899899 </CodeGroupItem>
900900
901901 ```python Python
about-claude/use-case-guides/ticket-routing Changed · +5 / -5 lines
from line 6
66
77## Prerequisites
88
9* A Claude API key and the Claude SDK installed
9* A Claude API key and the Anthropic SDK installed
1010* Access to, and familiarity with, your existing support ticketing system
1111* A sample set of historical support tickets for testing
1212
from line 693
693693
694694<CodeGroup exclude="shell">
695695 <CodeGroupItem language="cURL">
696 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
696 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
697697 </CodeGroupItem>
698698
699699 <CodeGroupItem language="CLI">
700 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
700 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
701701 </CodeGroupItem>
702702
703703 ```python Python
from line 1041
10411041
10421042<CodeGroup exclude="shell">
10431043 <CodeGroupItem language="cURL">
1044 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
1044 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
10451045 </CodeGroupItem>
10461046
10471047 <CodeGroupItem language="CLI">
1048 This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
1048 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
10491049 </CodeGroupItem>
10501050
10511051 ```python Python
agents-and-tools/agent-skills/claude-api-skill Changed · +19 / -1 lines
from line 138
138138The skill handles:
139139
140140* **Model ID swaps**, including typed SDK constants (`Model.CLAUDE_OPUS_4_8` → `Model.CLAUDE_OPUS_5_5`) across all supported languages, and classifying each file as a caller, a model definer, or an opaque string reference before editing
141
141142* **Cloud platform detection**, preserving platform-specific model ID formats (for example, the `anthropic.` prefix on Amazon Bedrock) and skipping changes for features that are unavailable on partner-operated platforms
143
142144* **Breaking parameter changes**, such as removing `temperature`, `top_p`, and `top_k` for Claude Opus 4.8 and Claude Opus 4.7, and converting `thinking: {type: "enabled", budget_tokens: N}` to `thinking: {type: "adaptive"}`
145
143146* **Prefill replacement**, converting assistant-message prefill patterns to [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) where applicable
147
144148* **Beta header cleanup**, removing beta headers that the target model doesn’t require (for example, `effort-2025-11-24`, `fine-grained-tool-streaming-2025-05-14`, `interleaved-thinking-2025-05-14`) and switching back from `client.beta.messages.create()` (go: `client.Beta.Messages.New()`; java: `client.beta().messages().create()`; csharp: `client.Beta.Messages.Create()`; php: `$client->beta->messages->create()`) to `client.messages.create()` (go: `client.Messages.New()`; java: `client.messages().create()`; csharp: `client.Messages.Create()`; php: `$client->messages->create()`)
149
145150* **Effort calibration**, recommending an `output_config.effort` starting point for the target model (for example, the default `high` on Claude Opus 5, and `xhigh` for coding and agentic use cases on Claude Opus 4.8 and Claude Opus 4.7)
151
146152* **Prompt-behavior tuning**, flagging length-control, tool-triggering, subagent, and instruction-following prompts that might behave differently on the target model
153
147154* **Silent default handling**, opting back into thinking summarization (`thinking.display: "summarized"`) when reasoning is surfaced to users on Claude Opus 4.8 and Claude Opus 4.7
148* **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) when the target is Claude Fable 5.2, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5 (the server-side `fallbacks` parameter, typically in its `"default"` mode, the SDK refusal-fallback middleware, or a fallback-credit retry), and updating fallback code written against earlier preview shapes
155
156* **Refusal fallback configuration**, in three parts:
157
158 * Adding `stop_reason: "refusal"` handling before reading response content.
159
160 * Updating fallback code written against earlier preview shapes.
161
162 * Setting up a [fallback retry path](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) for six target models. They are Claude Fable 5.2, Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5. The path uses one of these:
163
164 * [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback): the `fallbacks` parameter, typically in its `"default"` mode.
165 * [Client-side fallback with the SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback).
166 * A retry that redeems a [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit).
149167
150168As it edits, the skill explains each change and its motivation inline. On completion, it produces a checklist of items that require manual verification (typically integration tests, length-control prompt tuning, and cost/rate-limit re-baselining).
151169
agents-and-tools/tool-use/advisor-tool Changed · +32 / -7 lines
from line 443
443443
444444Pass the full assistant content, including `advisor_tool_result` blocks, back to the API in later requests. Round-trip the result blocks verbatim. With the newest Opus model as the advisor, as in this example, the result block’s `content` is the encrypted `advisor_redacted_result` variant. In the next request, the server decrypts it and renders the advice into the executor’s prompt (see [Result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants)). The mechanics are identical for any advisor model.
445445
446<CodeGroup exclude="shell">
446<CodeGroup exclude="shell:cURL, shell:CLI">
447 <CodeGroupItem language="cURL">
448 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
449 </CodeGroupItem>
450
451 <CodeGroupItem language="CLI">
452 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
453 </CodeGroupItem>
454
447455 ```python Python
448456 client = anthropic.Anthropic()
449457
from line 752
744752 ```
745753</CodeGroup>
746754
747You can drop the advisor tool from `tools` in a follow-up request while the message history still contains `advisor_tool_result` blocks, as long as no advisor call is [still pending](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#resuming-a-paused-turn). The API accepts the request and keeps the historical blocks, but the model cannot call the advisor in that request. You must still send the `advisor-tool-2026-03-01` beta header for those history blocks to be accepted. That covers the `advisor_tool_result` blocks, not thinking blocks. Removing the advisor tool, or changing its `model` or `caching`, is an [edit to `tools`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#what-counts-as-an-edit), and it invalidates the thinking blocks already in the history. Where the API enforces the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), the request then returns a 400 error. The API enforces it on every account when the executor is Claude Fable 5.2 or Claude Mythos 5.2, and for other executors wherever the table in [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement) shows it. To drop those blocks and continue, set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"` (beta, `thinking-binding-controls-2026-08-01` header) on that request and on every later request in the conversation.
755You can drop the advisor tool from `tools` in a follow-up request while the message history still contains `advisor_tool_result` blocks. The API accepts the request and keeps the historical blocks, but the model cannot call the advisor in that request. Two conditions apply:
748756
757* **No advisor call is still pending.** See [Resuming a paused turn](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#resuming-a-paused-turn).
758* **You still send the `advisor-tool-2026-03-01` beta header.** The API needs it to accept those history blocks. That header covers the `advisor_tool_result` blocks, not thinking blocks.
759
760**Exception: a history that also contains thinking blocks.** Removing the advisor tool is an [edit to `tools`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#what-counts-as-an-edit). So is changing its `model` or `caching`. An edit to `tools` invalidates the thinking blocks already in the history.
761
762* **What happens:** Where the API enforces the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), the request returns a 400 error.
763* **Where the API enforces it:** On every account when the executor is Claude Fable 5.2 or Claude Mythos 5.2. For other executors, see the table in [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement).
764* **How to continue:** Set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"` on that request and on every later request in the conversation. The API then drops those thinking blocks. This setting is in beta and needs the `thinking-binding-controls-2026-08-01` beta header.
765
749766<Note>
750 The advisor tool has no built-in conversation-level cap. To limit advisor calls across a conversation, count them client-side. When you reach your ceiling, remove the advisor tool from your `tools` array. You do not need to strip `advisor_tool_result` blocks from your message history. Where the prefix check is enforced, read the preceding paragraph first: the request returns a 400 error unless you set `"drop_block"`.
767 The advisor tool has no built-in conversation-level cap. To limit advisor calls across a conversation, count them client-side. When you reach your ceiling, remove the advisor tool from your `tools` array. You do not need to strip `advisor_tool_result` blocks from your message history. If your history also contains thinking blocks, read the preceding exception first. In that case, where the prefix check is enforced, the request returns a 400 error unless you set `"drop_block"`.
751768</Note>
752769
753770### Resuming a paused turn
from line 777
760777
761778With the default `NUDGE_TURN` of 2, the reminder typically arrives after the model has oriented on the task but before it has committed to an approach.
762779
763<CodeGroup exclude="shell">
780<CodeGroup exclude="shell:cURL, shell:CLI">
781 <CodeGroupItem language="cURL">
782 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
783 </CodeGroupItem>
784
785 <CodeGroupItem language="CLI">
786 This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it.
787 </CodeGroupItem>
788
764789 ```python Python
765790 client = anthropic.Anthropic()
766791
from line 1449
14241449
14251450**When to enable it:** The cache write costs more than the reads save when the advisor is called two or fewer times in each conversation. Caching breaks even at roughly three advisor calls and improves from there. Enable it for long agent loops, and keep it off for short tasks.
14261451
1427**Keep it consistent:** Set `caching` once and leave it for the whole conversation. Toggling it off and on mid-conversation causes cache misses. Where the prefix check is enforced, the toggle is also an edit to `tools`, and the next request returns a 400 error unless you set `"drop_block"`, as [Multi-turn conversations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#multi-turn-conversations) explains.
1452**Keep it consistent:** Set `caching` once and leave it for the whole conversation. Toggling it off and on mid-conversation causes cache misses. Each toggle is also an edit to `tools`. That edit can make the next request return a 400 error. [Multi-turn conversations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#multi-turn-conversations) explains when this happens and what to set.
14281453
14291454<Warning>
14301455 [`clear_thinking`](https://platform.claude.com/docs/en/build-with-claude/context-editing) with a `keep` value other than `"all"` shifts the advisor’s quoted transcript each turn, causing advisor-side cache misses. This is a cost degradation only. Advice quality is unaffected. When thinking is on without explicit `clear_thinking` configuration, the API defaults to `keep: {type: "thinking_turns", value: 1}`, which triggers this behavior (the default on earlier Opus and Sonnet models and on Haiku models through Claude Haiku 4.5, whereas on Claude Opus 4.5 and later Opus models, Claude Sonnet 4.6 and later Sonnet models, and Claude Haiku 5.5, the default is to keep all turns). Set `keep: "all"` to preserve advisor cache stability.
from line 1722
16971722(Advisor: please keep your guidance under 80 words. I need a focused starting point, not a comprehensive plan.)
16981723```
16991724
1700This line can be prefixed programmatically by your agent framework before sending the request. The limit is a soft constraint. The advisor occasionally exceeds it, so ask for roughly 80 percent of your true ceiling.
1725Your agent framework can prefix this line programmatically before sending the request. The limit is a soft constraint. The advisor occasionally exceeds it, so ask for roughly 80 percent of your true ceiling.
17011726
17021727<Note>
17031728 In Anthropic’s testing this line also increased how often the executor consults the advisor, but the net effect was still lower total cost (more consults, each shorter).
from line 1853
18281853
18291854### Cost control
18301855
1831* For conversation-level budgets, count advisor calls client-side. When you reach your cap, remove the advisor tool from `tools`; you do not need to strip `advisor_tool_result` blocks from your message history (see the note in [Multi-turn conversations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#multi-turn-conversations)). Where the API enforces the prefix check, the request that removes the tool returns a 400 error unless you set `prefix_mismatch_behavior` to `"drop_block"`, as that section explains. The API enforces the check for every account when the executor is Claude Fable 5.2 or Claude Mythos 5.2.
1856* For conversation-level budgets, count advisor calls client-side. When you reach your cap, remove the advisor tool from `tools`. You do not need to strip `advisor_tool_result` blocks from your message history (see the note in [Multi-turn conversations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#multi-turn-conversations)). If you send earlier thinking blocks back, removing the tool can return a 400 error where the API enforces the prefix check. To avoid it, set `prefix_mismatch_behavior` to `"drop_block"`, as [Multi-turn conversations](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#multi-turn-conversations) explains. The API enforces the check for every account when the executor is Claude Fable 5.2 or Claude Mythos 5.2.
18321857* Enable `caching` only for conversations where you expect three or more advisor calls.
18331858
18341859## Model compatibility
agents-and-tools/tool-use/bash-tool Changed · +5 / -5 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel): stable
33 Amazon Bedrock (bedrock-runtime): stable
34 Claude Platform on AWS: stable
3535 Claude Models on Google Cloud (Google managed): stable
3636 Microsoft Foundry: stable
3737---
from line 2013
20132013
20142014* Availability: Available
20152015
2016| Status | Cloud platforms |
2017| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2018| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
2016| Status | Cloud platforms |
2017| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2018| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
20192019
20202020### Data handling
20212021
agents-and-tools/tool-use/browser-use-sdk Changed · +6 / -5 lines
from line 20
2020 - claude-opus-4-8
2121 supportedPlatforms:
2222 Claude API: beta
23 Claude Platform on AWS: beta
2423 Amazon Bedrock: beta
24 Claude Platform on AWS: beta
2525 Claude Models on Google Cloud (Google managed): beta
2626 Microsoft Foundry: beta
2727---
from line 1389
13891389
13901390* Availability: Available
13911391
1392| Status | Cloud platforms | Models |
1393| ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1394| Beta | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1395| Beta | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1392| Status | Cloud platforms | Models |
1393| ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1394| Beta | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1395| Beta | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1396| Beta | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
13961397
13971398#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
13981399
agents-and-tools/tool-use/browser-use-tool Changed · +12 / -9 lines
from line 23
2323 - claude-opus-4-8
2424 supportedPlatforms:
2525 Claude API: stable
26 Claude Platform on AWS: stable
2726 Amazon Bedrock: stable
27 Amazon Bedrock (bedrock-runtime): stable
28 Claude Platform on AWS: stable
2829 Claude Models on Google Cloud (Google managed): stable
2930 Microsoft Foundry: stable
3031---
from line 1575
15741575
15751576## Pricing and data retention
15761577
1577Browser use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:
1578Browser use follows the standard [tool use pricing in the tool use overview](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:
15781579
1579**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
1580**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request: about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models. These tokens cover the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The response `usage` reports the exact count for a request, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
15801581
15811582**Additional token consumption:**
15821583
1583* Screenshot and zoom images returned in tool results, billed as image input (see [Vision pricing](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
1584* Screenshot and zoom images returned in tool results, billed as image input (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
15841585* Text tool results returned to Claude, such as accessibility trees, page text, and console or network entries
15851586
15861587<Note>
from line 1624
16231624
16241625* Availability: Available
16251626
1626| Status | Cloud platforms | Models |
1627| --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1628| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1629| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1627| Status | Cloud platforms | Models |
1628| --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1629| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1630| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1631| Available | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
1632| Available | [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
16301633
16311634#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
16321635
agents-and-tools/tool-use/build-a-tool-using-agent Changed · +10 / -10 lines
from line 20
2020
2121<CodeGroup exclude="shell:cURL, shell:CLI">
2222 <CodeGroupItem language="cURL">
23 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
23 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
2424 </CodeGroupItem>
2525
2626 <CodeGroupItem language="CLI">
27 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
27 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
2828 </CodeGroupItem>
2929
3030 ```python Python
from line 844
844844
845845<CodeGroup exclude="shell:cURL, shell:CLI">
846846 <CodeGroupItem language="cURL">
847 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
847 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
848848 </CodeGroupItem>
849849
850850 <CodeGroupItem language="CLI">
851 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
851 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
852852 </CodeGroupItem>
853853
854854 ```python Python
from line 1607
16071607
16081608<CodeGroup exclude="shell:cURL, shell:CLI">
16091609 <CodeGroupItem language="cURL">
1610 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
1610 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
16111611 </CodeGroupItem>
16121612
16131613 <CodeGroupItem language="CLI">
1614 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
1614 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
16151615 </CodeGroupItem>
16161616
16171617 ```python Python
from line 2417
24172417
24182418<CodeGroup exclude="shell:cURL, shell:CLI">
24192419 <CodeGroupItem language="cURL">
2420 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
2420 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
24212421 </CodeGroupItem>
24222422
24232423 <CodeGroupItem language="CLI">
2424 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
2424 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
24252425 </CodeGroupItem>
24262426
24272427 ```python Python
from line 3319
33193319
33203320<CodeGroup exclude="shell:cURL, shell:CLI">
33213321 <CodeGroupItem language="cURL">
3322 The tool runner is a helper in the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview). Raw HTTP requests have no equivalent.
3322 The tool runner is a helper in the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview). Raw HTTP requests have no equivalent.
33233323 </CodeGroupItem>
33243324
33253325 <CodeGroupItem language="CLI">
3326 The tool runner is a helper in the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview). The `ant` CLI has no equivalent.
3326 The tool runner is a helper in the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview). The `ant` CLI has no equivalent.
33273327 </CodeGroupItem>
33283328
33293329 ```python Python
agents-and-tools/tool-use/computer-use-tool Changed · +30 / -22 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel): beta
33 Amazon Bedrock (bedrock-runtime): stable
34 Claude Platform on AWS: stable
3535 Claude Models on Google Cloud (Google managed): stable
3636 Microsoft Foundry: stable
3737 details:
from line 70
7070
7171This extra protection isn’t ideal for every use case (for example, use cases without a human in the loop), so if you’d like to opt out and turn it off, [contact support](https://support.claude.com/en/). The precautions listed earlier remain important even with these classifiers in place.
7272
73Inform end users of relevant risks and obtain their consent prior to enabling computer use in your own products.
73Inform end users of relevant risks and obtain their consent before enabling computer use in your own products.
7474
7575## Quick start
7676
from line 511
511511 ): Promise<Anthropic.MessageParam[]> {
512512 // Run the computer-use agent loop until Claude stops requesting tools
513513 // or the iteration limit is reached.
514 for (let i = 0; i < maxIterations; i++) {
514 for (let iteration = 0; iteration < maxIterations; iteration++) {
515515 const response = await client.messages.create({
516516 model,
517517 max_tokens: 4096,
from line 545
545545 {
546546 // Run the computer-use agent loop until Claude stops requesting tools
547547 // or the iteration limit is reached.
548 for (var i = 0; i < maxIterations; i++)
548 for (var iteration = 0; iteration < maxIterations; iteration++)
549549 {
550550 var response = await client.Messages.Create(
551551 new MessageCreateParams
from line 619
619619 * or the iteration limit is reached.
620620 */
621621 List<MessageParam> samplingLoop(Model model, List<MessageParam> messages, int maxIterations) {
622 for (int i = 0; i < maxIterations; i++) {
622 for (int iteration = 0; iteration < maxIterations; iteration++) {
623623 Message response = client.messages().create(MessageCreateParams.builder()
624624 .model(model)
625625 .maxTokens(4096)
from line 648
648648 * Run the computer-use agent loop until Claude stops requesting tools
649649 * or the iteration limit is reached.
650650 */
651 function samplingLoop(string $model, array $messages, int $maxIterations = 10): array
651 function samplingLoop(Model|string $model, array $messages, int $maxIterations = 10): array
652652 {
653653 global $client, $tools;
654654
655 for ($i = 0; $i < $maxIterations; $i++) {
655 for ($iteration = 0; $iteration < $maxIterations; $iteration++) {
656656 $response = $client->messages->create(
657657 model: $model,
658658 maxTokens: 4096,
from line 1554
15541554 response.content.each do |block|
15551555 # This example declares only the computer toolset; route other tools here
15561556 # if you add them.
1557 next unless block.type == :tool_use && block.toolset_name == "computer"
1557 next unless block.is_a?(Anthropic::Models::ToolUseBlock) && block.toolset_name == "computer"
15581558
15591559 result = { type: "tool_result", tool_use_id: block.id, toolset_name: "computer" }
15601560 if failed
from line 1609
16091609Screenshots and zoom images that you return to the computer use toolset must already fit within your model’s [image size limits](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size): the toolset takes no display dimensions and the API doesn’t downscale for you, so an oversized `tool_result` image is rejected with a validation error. Because Claude returns coordinates in the pixel space of the image it receives, keep the scale factor you used so you can map those coordinates back to your screen.
16101610
16111611<Note>
1612 Limits vary by model. Claude Opus 4.7 and later models, including every model that supports `computer_toolset_20260801`, accept up to 2,576 pixels on the long edge and 4,784 visual tokens total (`⌈width / 28⌉ × ⌈height / 28⌉`, approximately 3.75 megapixels); earlier models accept up to 1,568 pixels on the long edge and approximately 1.15 megapixels total (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size) for each model’s tier). The following example uses the earlier-model 1,568 px / 1.15 MP limits. For a high-resolution-tier model, size to the visual-token limit rather than a pixel total, for example with the resize helper in [Resize your image before uploading](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates#resize-your-image-before-uploading).
1612 Limits vary by model. Claude Opus 4.7 and later models, including every model that supports `computer_toolset_20260801`, accept up to 2,576 pixels on the long edge and 4,784 visual tokens total (`⌈width / 28⌉ × ⌈height / 28⌉`, approximately 3.75 megapixels). Earlier models accept up to 1,568 pixels on the long edge and approximately 1.15 megapixels total. See [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size) for each model’s tier. The following example uses the earlier-model 1,568 px / 1.15 MP limits. For a high-resolution-tier model, size to the visual-token limit rather than a pixel total, for example with the resize helper in [Resize your image before uploading](https://platform.claude.com/docs/en/build-with-claude/vision-coordinates#resize-your-image-before-uploading).
16131613</Note>
16141614
16151615If your screen is larger than the limit, resize each screenshot before returning it and scale Claude’s returned coordinates back to the original screen space. Because the toolset takes no display dimensions, the resize and the coordinate scaling in your application code are all you need:
from line 1829
18291829To keep [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) effective while bounding context:
18301830
18311831* Place one `cache_control` breakpoint after the system prompt and tool definitions, and up to three more on the last `tool_result` block of each of the most recent turns, advancing them each turn. Within a [batch action](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#batch-actions), markers on several blocks act as a single breakpoint, but each still counts toward the limit of four, so use at most one in any turn.
1832
18321833* Prune old screenshots in *batches*, not one each turn. Dropping a screenshot every turn changes the prefix every turn and invalidates the cache. A reasonable default is to keep the last three screenshots and prune every 25 turns, so the prefix stays byte-identical between prune events; if your screenshots exceed the stricter limit, choose an interval that keeps each request at 20 or fewer images.
1833* On Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, avoid pruning on the client: removing an earlier screenshot from a request [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in that request and in every later request. Resize screenshots to stay under the stricter limit instead and use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context. If you must prune, keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on; after each prune, Claude continues without the thinking produced since the pruned screenshot, on that request and every later one. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With any other thinking setting on those models, keep the history append-only or strip every `thinking` and `redacted_thinking` block after the pruned screenshot.
18341834
1835* Avoid client-side pruning on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1. The same goes for Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. On these models, removing an earlier screenshot from a request [invalidates every later thinking block already in the history](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) of that and every later request.
1836
1837 * **Instead:** Resize screenshots to stay under the stricter limit. Use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context.
1838 * **If you must prune:** Keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on. After each prune, the API drops the invalidated thinking blocks, on that request and every later one. So Claude continues without the thinking that it produced after the pruned screenshot.
1839 * **If you must prune on Claude Sonnet 5.5 or Claude Haiku 5.5:** `prefix_mismatch_behavior` works only with `thinking: {"type": "adaptive"}`. With any other thinking setting on those models, keep the history append-only or strip every `thinking` and `redacted_thinking` block after the pruned screenshot.
1840
18351841### Diagnose click issues
18361842
18371843If clicks miss their targets, the cause is usually one of the following:
from line 2190
21842190| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21852191| `computer_20250124` | `computer-use-2025-01-24` | Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Haiku 4.5, Claude Opus 4.1 ([retired, except on Claude Models on Google Cloud (Google managed) and Bedrock](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Sonnet 4 ([retired, except on Claude Models on Google Cloud (Google managed) and Bedrock](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Opus 4 ([retired, except on Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |
21862192
2187On Amazon Bedrock, Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header.
2193On Amazon Bedrock, Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. With Amazon Bedrock’s InvokeModel API, send `computer-use-2025-11-24` in the `anthropic_beta` array of the request body instead of in a header. For that API, see [Claude on Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy).
21882194
21892195***
21902196
from line 2215
22092215
22102216## Pricing
22112217
2212Computer use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:
2218Computer use follows the standard [tool use pricing in the tool use overview](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:
22132219
2214**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
2220**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request: about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models. These tokens cover the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The response `usage` reports the exact count for a request, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).
22152221
22162222**Earlier tool versions:** The following figures apply to the `computer_20251124` and `computer_20250124` tool versions, not to `computer_toolset_20260801`:
22172223
22182224* System prompt overhead: 466–499 tokens added to the system prompt
2219* Tool definition: about 735 input tokens per tool definition (measured with `computer_20250124`)
2225* Tool definition: about 735 input tokens for each tool definition (measured with `computer_20250124`)
22202226
22212227**Additional token consumption:**
22222228
2223* Screenshot and zoom images returned in tool results, billed as image input (see [Vision pricing](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
2229* Screenshot and zoom images returned in tool results, billed as image input (see [Resolution and token cost](https://platform.claude.com/docs/en/build-with-claude/vision#evaluate-image-size))
22242230* Tool execution results returned to Claude
22252231
22262232<Note>
from line 2271
22652271
22662272* Availability: Available
22672273
2268| Status | Cloud platforms | Models |
2269| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2270| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2271| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2272| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
2274| Status | Cloud platforms | Models |
2275| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2276| Available | Claude API, [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), Claude Mythos Preview, [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2277| Available | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2278| Available | [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2279| Available | [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview), [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview), [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview), [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview), [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview), [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview), [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview) |
2280| Beta | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
22732281
22742282#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
22752283
agents-and-tools/tool-use/define-tools Changed · +6 / -6 lines
from line 26
2626 - claude-sonnet-4-5-20250929
2727 supportedPlatforms:
2828 Claude API: stable
29 Amazon Bedrock: stable
30 Amazon Bedrock (bedrock-runtime): stable
2931 Claude Platform on AWS: stable
3032 Claude Models on Google Cloud (Anthropic managed): stable
31 Amazon Bedrock: stable
32 Amazon Bedrock (InvokeModel): stable
3333 Claude Models on Google Cloud (Google managed): stable
3434 Microsoft Foundry: stable
3535---
from line 589
589589
590590Not every model and setting supports forced tool use. Where it isn’t supported, `tool_choice: {"type": "any"}` and `tool_choice: {"type": "tool", "name": "..."}` fail, whereas `tool_choice: {"type": "auto"}` (the default) and `tool_choice: {"type": "none"}` still work:
591591
592| Model or setting | Restriction | What to use instead |
593| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
594| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn’t block forced tool use (models with thinking on by default, such as Claude Opus 5 and Claude Haiku 5.5, accept it, but a forced call skips thinking: the response starts with the tool call and has no `thinking` block); the models in the next row reject forced tool use regardless of thinking settings |
595| Claude Fable 5.2, [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) | `any` and `tool` return a [400 error](https://platform.claude.com/docs/en/api/errors#forced-tool-use-not-supported) | `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to guarantee schema-valid tool inputs, or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) when you need a response in a fixed JSON shape. Prompting still influences which tool `auto` picks. `none` is also supported |
592| Model or setting | Restriction | What to use instead |
593| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
594| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn’t block forced tool use (models with thinking on by default, such as Claude Opus 5 and Claude Haiku 5.5, accept it, but a forced call skips thinking: the response starts with the tool call and has no `thinking` block); the models in the next row reject forced tool use regardless of thinking settings |
595| Claude Fable 5.2, [Claude Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview), Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) | `any` and `tool` return a 400 error. See [Forced tool use not supported](https://platform.claude.com/docs/en/api/errors#forced-tool-use-not-supported) | `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to guarantee schema-valid tool inputs, or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) when you need a response in a fixed JSON shape. Prompting still influences which tool `auto` picks. `none` is also supported |
596596
597597On models that support it, the highlighted lines are the only difference from a standard tool use request:
598598
agents-and-tools/tool-use/fine-grained-tool-streaming Changed · +7 / -7 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel): stable
33 Amazon Bedrock (bedrock-runtime): stable
34 Claude Platform on AWS: stable
3535 Claude Models on Google Cloud (Google managed): stable
3636 Microsoft Foundry: stable
3737---
from line 524
524524
525525<CodeGroup exclude="shell">
526526 <CodeGroupItem language="cURL">
527 Accumulating the input fragments of each `tool_use` block needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this. To see the raw fragments as they stream, run the request in [How to use fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#how-to-use-fine-grained-tool-streaming).
527 Accumulating the input fragments of each `tool_use` block needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this. To see the raw fragments as they stream, run the request in [How to use fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#how-to-use-fine-grained-tool-streaming).
528528 </CodeGroupItem>
529529
530530 <CodeGroupItem language="CLI">
531 Accumulating the input fragments of each `tool_use` block needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this. To see the raw fragments as they stream, run the request in [How to use fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#how-to-use-fine-grained-tool-streaming).
531 Accumulating the input fragments of each `tool_use` block needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this. To see the raw fragments as they stream, run the request in [How to use fine-grained tool streaming](https://platform.claude.com/docs/en/agents-and-tools/tool-use/fine-grained-tool-streaming#how-to-use-fine-grained-tool-streaming).
532532 </CodeGroupItem>
533533
534534 ```python Python
from line 975
975975
976976* Availability: Available
977977
978| Status | Cloud platforms |
979| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
980| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
978| Status | Cloud platforms |
979| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
980| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
981981
982982### Data handling
983983
agents-and-tools/tool-use/overview Changed · +3 / -3 lines
from line 144
144144
145145<CodeGroup exclude="shell:cURL, shell:CLI">
146146 <CodeGroupItem language="cURL">
147 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
147 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
148148 </CodeGroupItem>
149149
150150 <CodeGroupItem language="CLI">
151 This workflow needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
151 This workflow needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
152152 </CodeGroupItem>
153153
154154 ```python Python
from line 786
786786
787787These token counts are added to your normal input and output tokens to calculate the total cost of a request.
788788
789See the [Models overview](https://platform.claude.com/docs/en/models/overview#latest-models-comparison) table for current per-model prices.
789See the [All models](https://platform.claude.com/docs/en/models/overview#all-models) table for current per-model prices.
790790
791791When you send a tool use prompt, like any other API request, the response includes both input and output token counts in the reported `usage` metrics.
792792
agents-and-tools/tool-use/parallel-tool-use Changed · +10 / -10 lines
from line 25
2525 - claude-sonnet-4-5-20250929
2626 supportedPlatforms:
2727 Claude API: stable
28 Claude Platform on AWS: stable
2928 Amazon Bedrock: stable
30 Amazon Bedrock (InvokeModel): stable
29 Amazon Bedrock (bedrock-runtime): stable
30 Claude Platform on AWS: stable
3131 Claude Models on Google Cloud (Google managed): stable
3232 Microsoft Foundry: stable
3333---
from line 63
6363
6464<CodeGroup exclude="shell">
6565 <CodeGroupItem language="cURL">
66 This end-to-end test needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it. The request it sends is a standard tool use request with two tools defined.
66 This end-to-end test needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it. The request it sends is a standard tool use request with two tools defined.
6767 </CodeGroupItem>
6868
6969 <CodeGroupItem language="CLI">
70 This end-to-end test needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
70 This end-to-end test needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) to run it.
7171 </CodeGroupItem>
7272
7373 ```python Python
from line 1158
11581158
11591159### Exactly one tool call
11601160
1161When the `tool_choice` type is `any` or `tool`, setting `disable_parallel_tool_use: true` means Claude calls exactly one tool. Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 don’t support these `tool_choice` types (see [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use)). The following example uses `any`. The same field works with `tool`:
1161When the `tool_choice` type is `any` or `tool`, setting `disable_parallel_tool_use: true` means Claude calls exactly one tool. Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, and Claude Sonnet 5.5 don’t support these `tool_choice` types (see [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use)). The following example uses `any`. The same field works with `tool`:
11621162
11631163<CodeGroup>
11641164 ```bash cURL
from line 1479
14791479
14801480<CodeGroup exclude="shell">
14811481 <CodeGroupItem language="cURL">
1482 To measure parallel tool use, your code analyzes the responses that it already collected. This needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this.
1482 To measure parallel tool use, your code analyzes the responses that it already collected. This needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this.
14831483 </CodeGroupItem>
14841484
14851485 <CodeGroupItem language="CLI">
1486 To measure parallel tool use, your code analyzes the responses that it already collected. This needs more logic than a single shell command. Use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this.
1486 To measure parallel tool use, your code analyzes the responses that it already collected. This needs more logic than a single shell command. Use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) for this.
14871487 </CodeGroupItem>
14881488
14891489 ```python Python
from line 1631
16311631* Availability: On by default
16321632* Usage: To turn it off, set `disable_parallel_tool_use: true` inside `tool_choice`.
16331633
1634| Status | Cloud platforms |
1635| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1636| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
1634| Status | Cloud platforms |
1635| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1636| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
16371637
16381638#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
16391639
agents-and-tools/tool-use/strict-tool-use Changed · +5 / -5 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel): stable
33 Amazon Bedrock (bedrock-runtime): stable
34 Claude Platform on AWS: stable
3535 Claude Models on Google Cloud (Google managed): stable
3636 Microsoft Foundry: stable
3737---
from line 1183
11831183
11841184* Availability: Available
11851185
1186| Status | Cloud platforms | Models |
1187| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
1188| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [All models](https://platform.claude.com/docs/en/models/overview) |
1186| Status | Cloud platforms | Models |
1187| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
1188| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [All models](https://platform.claude.com/docs/en/models/overview) |
11891189
11901190### Data handling
11911191
agents-and-tools/tool-use/text-editor-tool Changed · +5 / -5 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel): stable
33 Amazon Bedrock (bedrock-runtime): stable
34 Claude Platform on AWS: stable
3535 Claude Models on Google Cloud (Google managed): stable
3636 Microsoft Foundry: stable
3737---
from line 2314
23142314
23152315* Availability: Available
23162316
2317| Status | Cloud platforms |
2318| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2319| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
2317| Status | Cloud platforms |
2318| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2319| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
23202320
23212321### Data handling
23222322
agents-and-tools/tool-use/tool-search-tool Changed · +4 / -4 lines
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: stable
32 Claude Platform on AWS: stable
3332 Amazon Bedrock: stable
34 Amazon Bedrock (InvokeModel):
33 Amazon Bedrock (bedrock-runtime):
3534 availability: stable
3635 note: On Amazon Bedrock it is not available through the Converse API.
36 Claude Platform on AWS: stable
3737 Claude Models on Google Cloud (Google managed): stable
3838 Microsoft Foundry: stable
3939---
from line 916
916916
917917| Status | Cloud platforms | Models |
918918| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
919| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [All models](https://platform.claude.com/docs/en/models/overview) |
920| Available<sup>1</sup> | [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | [All models](https://platform.claude.com/docs/en/models/overview) |
919| Available | Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) | [All models](https://platform.claude.com/docs/en/models/overview) |
920| Available<sup>1</sup> | [Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) | [All models](https://platform.claude.com/docs/en/models/overview) |
921921
9229221. On Amazon Bedrock it is not available through the Converse API.
923923
api/errors Changed · +5 / -5 lines
from line 267
267267
268268If you are building a direct API integration, setting a [TCP socket keep-alive](https://tldp.org/HOWTO/TCP-Keepalive-HOWTO/programming.html) can reduce the impact of idle connection timeouts on some networks.
269269
270The [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) validates that your non-streaming Messages API requests are not expected to exceed a 10-minute timeout. It also sets a socket option for TCP keep-alive.
270The [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) validates that your non-streaming Messages API requests are not expected to exceed a 10-minute timeout. It also sets a socket option for TCP keep-alive.
271271
272272If you don’t need to process events incrementally, the SDK can consume the stream for you and return the complete `Message` object, identical to what a non-streaming call returns:
273273
274274<CodeGroup exclude="shell:cURL">
275275 <CodeGroupItem language="cURL">
276 A curl request prints the raw stream events and can’t combine them into the final message. To get the complete `Message` object from a stream, use the [Claude SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview).
276 A curl request prints the raw stream events and can’t combine them into the final message. To get the complete `Message` object from a stream, use the [Anthropic SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview).
277277 </CodeGroupItem>
278278
279279 ```bash CLI
from line 540
540540
541541The Claude API returns the same message for any Anthropic-defined tool type that the requested model doesn’t support. Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support computer use through the `computer_toolset_20260801` toolset. Declare `{"type": "computer_toolset_20260801"}` without the beta header and update your agent loop as described in [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.
542542
543On Amazon Bedrock, Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) lists the models to use with each earlier version.
543On Amazon Bedrock, Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 also accept the `computer_20251124` tool with the `computer-use-2025-11-24` beta header. With Amazon Bedrock’s InvokeModel API, send `computer-use-2025-11-24` in the `anthropic_beta` array of the request body instead of in a header. For that API, see [Claude on Amazon Bedrock (bedrock-runtime)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy). [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) lists the models to use with each earlier version.
544544
545545### Thinking block bound to a different conversation
546546
547This 400 `invalid_request_error` usually means a thinking block you sent back failed the prefix check: something before the block changed after the block was produced, such as the `system` prompt, `tools`, or an earlier message. Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 run this check. For requests that don’t set `prefix_mismatch_behavior`, [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement) shows which ones get this error. The message starts with the position of the first failing block:
547This 400 `invalid_request_error` usually means a thinking block you sent back failed the prefix check: something before the block changed after the block was produced, such as the `system` prompt, `tools`, or an earlier message. Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 run this check. For requests that don’t set `prefix_mismatch_behavior`, whether they get this error depends on the model and the account. See [When `prefix_mismatch_behavior` is unset](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#enforcement). The message starts with the position of the first failing block:
548548
549549```text wrap
550550messages.{i}.content.{j}: Invalid `signature` in `thinking` block. The block is bound to a different conversation. Remove the block, or set `thinking.block_binding.prefix_mismatch_behavior` to "drop_block".
551551```
552552
553Without the `thinking-binding-controls-2026-08-01` beta header, the message also names that header. Resending the same history fails the same way, even after you fix the code that made the edit. To continue the conversation, send the beta header with `prefix_mismatch_behavior: "drop_block"` on the retry and on every later request. Alternatively, strip the block the error names and every later `thinking` and `redacted_thinking` block, then retry once. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`, so with any other thinking setting, strip the blocks. To stop new conversations from failing, keep the history append-only. A block from a model the target model can’t read is dropped rather than rejected. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) and the [fix for an invalid thinking block signature](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-block-signature) in Troubleshooting thinking.
553Without the `thinking-binding-controls-2026-08-01` beta header, the message also names that header. Resending a history that holds the edit fails the same way, even after you fix the code that made the edit. To continue the conversation, send the beta header with `prefix_mismatch_behavior: "drop_block"` on the retry and on every later request. Alternatively, strip the block the error names and every later `thinking` and `redacted_thinking` block, leave them out of later requests, and retry. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`, so with any other thinking setting, strip the blocks. To stop new conversations from failing, keep the history append-only. A block from a model the target model can’t read is dropped rather than rejected. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) and the [fix for an invalid thinking block signature](https://platform.claude.com/docs/en/build-with-claude/thinking-troubleshooting#error-thinking-block-signature) in Troubleshooting thinking.
554554
555555Sending `thinking.block_binding` without the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers) returns a 400 `invalid_request_error` whose message ends in:
556556
api/opentelemetry/spans Changed · +4 / -4 lines
from line 1
11---
22title: OpenTelemetry span reference
33url: https://platform.claude.com/docs/en/api/opentelemetry/spans
4description: The OpenTelemetry spans and span attributes that the Claude API and the Claude SDK emit.
4description: The OpenTelemetry spans and span attributes that the Claude API and the Anthropic SDK emit.
55featureMetadata:
66 topic:
77 title: OpenTelemetry
from line 29
2929 - claude-sonnet-4-5-20250929
3030 supportedPlatforms:
3131 Claude API: beta
32 Amazon Bedrock: beta
33 Amazon Bedrock (bedrock-runtime): beta
3234 Claude Platform on AWS: beta
3335 Claude Models on Google Cloud (Anthropic managed): beta
34 Amazon Bedrock: beta
35 Amazon Bedrock (InvokeModel): beta
3636 Claude Models on Google Cloud (Google managed): beta
3737 Microsoft Foundry: beta
3838---
from line 41
4141 OpenTelemetry export is in beta. It’s provided under your agreement with Anthropic, including the Beta Services section of the [Service Specific Terms](https://www.anthropic.com/legal/service-specific-terms). Span names and attributes can change during the beta.
4242</Note>
4343
44To get spans, see [Set up OpenTelemetry with the Claude SDK](https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk) and [Set up OpenTelemetry with the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry/api).
44To get spans, see [Set up OpenTelemetry with the Anthropic SDK](https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk) and [Set up OpenTelemetry with the Claude API](https://platform.claude.com/docs/en/manage-claude/opentelemetry/api).
4545
4646## Span names and kinds
4747
api/overview Changed · +8 / -8 lines
from line 90
9090* **Feature availability varies by platform:** Anthropic-operated platforms include [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry); partner-operated platforms include Claude Models on Google Cloud (Google managed) and Amazon Bedrock. See each platform’s page for feature availability and timing.
9191* **Best for:** Existing cloud commitments, specific compliance requirements, consolidated cloud billing
9292
93| Platform | Provider | Documentation |
94| ------------------------------------------------- | ------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
95| Claude Models on Google Cloud (Google managed) | Google Cloud | [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |
96| Amazon Bedrock | AWS | [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) |
97| Claude Platform on AWS | AWS (Anthropic-operated) | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
98| Claude Models on Google Cloud (Anthropic managed) | Google Cloud (Anthropic-operated) | [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
99| Microsoft Foundry | Microsoft Azure (Anthropic-operated) | [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
93| Platform | Provider | Documentation |
94| ------------------------------------------------- | ------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
95| Claude Models on Google Cloud (Google managed) | Google Cloud | [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed) |
96| Amazon Bedrock | AWS | [Claude in Amazon Bedrock (`bedrock-mantle`)](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock) and [Claude on Amazon Bedrock (`bedrock-runtime`)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy) |
97| Claude Platform on AWS | AWS (Anthropic-operated) | [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
98| Claude Models on Google Cloud (Anthropic managed) | Google Cloud (Anthropic-operated) | [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
99| Microsoft Foundry | Microsoft Azure (Anthropic-operated) | [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
100100
101101<Note>
102102 Claude Managed Agents is available through the first-party Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), and [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed). For feature availability across platforms, see the [Features overview](https://platform.claude.com/docs/en/build-with-claude/overview).
from line 166
166166* **Spend limits:** Maximum monthly cost for API usage
167167* **Rate limits:** Maximum number of requests per minute (RPM) and tokens per minute (TPM)
168168
169You can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits) and your spend limits on the Console’s [Billing](https://platform.claude.com/settings/billing) page. For higher rate limits or a higher monthly spend cap, use **Request tier increase** on the **Rate limits** page.
169You can view your rate limits under [Rate limits in the Claude Console](https://platform.claude.com/usage/limits). Your spend limits are under [Spend limits in the Claude Console](https://platform.claude.com/settings/spend-limits) (`platform.claude.com/settings/spend-limits`). For higher rate limits or a higher monthly spend cap, use **Request tier increase** on the **Rate limits** page.
170170
171171For detailed information about limits, tiers, and the token bucket algorithm used for rate limiting, see [Rate limits](https://platform.claude.com/docs/en/api/rate-limits).
172172
api/rate-limits Changed · +11 / -7 lines
from line 32
3232 **[Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws):** The same monthly spend caps apply, and requests stop at the cap in the same way. Billing and tier increases work differently; see [Spend limits on Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#spend-limits).
3333</Note>
3434
35Each of the Start, Build, and Scale tiers carries a monthly spend cap, which is the maximum your organization can spend on the API each calendar month. You can view your organization’s monthly spend cap and set your own limit on the [Billing](https://platform.claude.com/settings/billing) page in the Claude Console.
35Each of the Start, Build, and Scale tiers carries a monthly spend cap. The cap is the maximum your organization can spend on the API each calendar month. You can view your organization’s monthly spend cap and set your own limit under [Spend limits in the Claude Console](https://platform.claude.com/settings/spend-limits) (`platform.claude.com/settings/spend-limits`).
3636
3737| Usage tier | Monthly spend cap |
3838| ---------- | ----------------- |
from line 67
6767You can also set your own spend limit below your tier’s cap to control costs:
6868
6969<Steps>
70 <Step title="Navigate to the Billing page">
71 In the Claude Console, go to the [Billing](https://platform.claude.com/settings/billing) page (`platform.claude.com/settings/billing`).
70 <Step title="Navigate to your spend limits">
71 Go to [Spend limits in the Claude Console](https://platform.claude.com/settings/spend-limits) (`platform.claude.com/settings/spend-limits`).
7272 </Step>
7373
7474 <Step title="Open the spend limit editor">
75 In the **Spend limits** section, click **Adjust limit** (or **Set limit** if no limit is currently set).
75 Next to your organization’s **Monthly spend limit**, click **Adjust limit** or **Set limit**.
7676 </Step>
7777
7878 <Step title="Adjust your spend limit">
from line 94
9494
9595### Cache-aware ITPM
9696
97Many API providers use a combined “tokens per minute” (TPM) limit that might include all tokens, both cached and uncached, input and output. **Claude’s default ITPM rate limits count only uncached input tokens.** This is a key advantage that makes the rate limits effectively higher than they might initially appear.
97**The API’s default ITPM rate limits count only uncached input tokens.** This makes the rate limits effectively higher than they might initially appear.
9898
9999ITPM rate limits are estimated at the beginning of each request, and the estimate is adjusted during the request to reflect the actual number of input tokens used.
100100
from line 122
122122
123123OTPM rate limits are evaluated in real time as output tokens are produced, counting only the actual tokens generated. The `max_tokens` parameter does not factor into OTPM rate limit calculations, so there is no rate limit downside to setting a higher `max_tokens` value.
124124
125Each row in the following tables has its own RPM, ITPM, and OTPM limits. Some rows cover several models that share one limit; see the notes under the tables. You can check your current rate limits and behavior on the [Rate limits](https://platform.claude.com/usage/limits) page in the Claude Console, or read the configured limits and set workspace limits programmatically with the [Rate Limits API](https://platform.claude.com/docs/en/manage-claude/rate-limits-api).
125Each row in the following tables has its own RPM, ITPM, and OTPM limits. Some rows cover several models that share one limit; see the notes that follow the tables. You can check your current rate limits and behavior on the [Rate limits](https://platform.claude.com/usage/limits) page in the Claude Console, or read the configured limits and set workspace limits programmatically with the [Rate Limits API](https://platform.claude.com/docs/en/manage-claude/rate-limits-api).
126126
127127<Note>
128128 Rate limits are shared across all `inference_geo` values. Requests with `inference_geo: "us"` and `inference_geo: "global"` draw from the same rate limit pool.
from line 228
228228
229229### Fast mode rate limits
230230
231When you use [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) with `speed: "fast"` on Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Opus 5, or Claude Opus 4.8, dedicated rate limits apply. They are separate from standard rate limits. Claude Opus 5.5 has a default fast mode rate limit in the Start, Build, and Scale tiers, so you don’t need to request access to use fast mode with it. Organizations in the Evaluation tier can use fast mode with Claude Opus 5.5 once they move to the Start, Build, or Scale tier. The same applies to Claude Fable 5.2. It also applies to Claude Mythos 5.2. Fast mode for Claude Opus 5 and Claude Opus 4.8 is in research preview. To see your fast mode rate limits, go to the [Rate limits](https://platform.claude.com/usage/limits) page in the Claude Console. When you exceed your fast mode rate limits, the API returns a `429` error with a `retry-after` header.
231When you use [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) with `speed: "fast"`, dedicated rate limits apply, separate from standard rate limits. They apply on Claude Fable 5.2, Claude Mythos 5.2, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8. Fast mode is in research preview for Claude Opus 5 and deprecated for Claude Opus 4.8.
232
233Claude Fable 5.2, Claude Mythos 5.2, and Claude Opus 5.5 have a default fast mode rate limit. The default limit applies in the Start, Build, and Scale tiers. You don’t need to request fast mode access for these models. Organizations in the Evaluation tier can use fast mode with these models once they move to the Start, Build, or Scale tier.
234
235To see your fast mode rate limits, go to the [Rate limits](https://platform.claude.com/usage/limits) page in the Claude Console. When you exceed your fast mode rate limits, the API returns a `429` error with a `retry-after` header.
232236
233237The response includes `anthropic-fast-*` headers that indicate your fast mode rate limit status. See [Fast mode rate limits](https://platform.claude.com/docs/en/build-with-claude/fast-mode#rate-limits) for details on these headers.
234238
api/service-tiers Changed · +4 / -15 lines
from line 5
55featureMetadata:
66 status: stable
77 supportedModels:
8 - claude-fable-5-2
9 - claude-mythos-5-2
10 - claude-fable-5-1
11 - claude-mythos-5-1
128 - claude-fable-5
13 - claude-mythos-5
14 - claude-mythos-preview
15 - claude-opus-5-5
16 - claude-opus-5
17 - claude-sonnet-5-5
18 - claude-sonnet-5
19 - claude-haiku-5-5
209 - claude-haiku-4-5-20251001
2110 - claude-opus-4-8
2211 - claude-opus-4-7
from line 250
261250
262251## Availability
263252
264Service tiers are available on every model.
253Service tiers are available on select models.
265254
266255### API support
267256
from line 259
270259* Availability: Available
271260* Usage: Needs a Priority Tier commitment, which is no longer sold. With one, requests use Priority Tier by default; set `service_tier` to `"standard_only"` to use only standard capacity.
272261
273| Status | Cloud platforms |
274| --------- | --------------- |
275| Available | Claude API |
262| Status | Cloud platforms | Models |
263| --------- | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
264| Available | Claude API | [Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/overview), [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-4-8/overview), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-4-7/overview), [Claude Opus 4.6](https://platform.claude.com/docs/en/models/opus-4-6/overview), [Claude Sonnet 4.6](https://platform.claude.com/docs/en/models/sonnet-4-6/overview), [Claude Opus 4.5](https://platform.claude.com/docs/en/models/opus-4-5/overview), [Claude Sonnet 4.5](https://platform.claude.com/docs/en/models/sonnet-4-5/overview) |
276265
277266#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
278267
api/versioning Changed · +4 / -4 lines
from line 1
11---
2title: Versions
2title: API versions
33url: https://platform.claude.com/docs/en/api/versioning
4description: "When making API requests, you must send an `anthropic-version` request header. For example, `anthropic-version: 2026-10-21`. If you are using the [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview), this is handled for you automatically."
4description: "When making API requests, you must send an `anthropic-version` request header. For example, `anthropic-version: 2026-10-21`. If you are using the [client SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview), it sets this header for you."
55---
66
77For any given API version, Anthropic preserves:
from line 26
2626
2727 * [Migrating to API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21) shows how to upgrade.
2828
29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry), and [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed). On [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), it’s available for Claude 4.7 and later models. For other models on Bedrock, see the [migration guide for API version 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
29 * Available on the Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). On Amazon Bedrock, it’s available for Claude 4.7 and later models. For earlier Claude models on Bedrock, [keep the API version that you use today](https://platform.claude.com/docs/en/api/migration-2026-10-21#availability).
3030
3131 * Messages API:
3232
from line 40
4040 * [RBAC group members](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/list), and the response to removing one, no longer return `group_id`. Use `rbac_group_id` instead.
4141 * [RBAC roles](https://platform.claude.com/docs/en/api/beta/organization/rbac_roles/list) no longer return `name`. Use `display_name` instead.
4242 * [Organization](https://platform.claude.com/docs/en/api/organization/rate_limits/list) and [workspace](https://platform.claude.com/docs/en/api/organization/workspaces/rate_limits/list) rate-limit entries, and the response to [setting a workspace’s rate limits](https://platform.claude.com/docs/en/api/organization/workspaces/rate_limits/update), no longer return `group_type`. Use `group.type` instead.
43 * [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list) no longer return `workspace_id`. Use `scope.workspace_id` instead, which gives the workspace’s real ID even for the Default Workspace (an all-workspaces key has no `workspace_id` in `scope`).
43 * [API keys](https://platform.claude.com/docs/en/api/organization/api_keys/list) no longer return `workspace_id`. Use `scope.workspace_id` instead. It holds the ID of the key’s workspace, the Default Workspace included. An all-workspaces key has no `scope.workspace_id`.
4444
4545 * Claude Enterprise Analytics API:
4646