456 pages for high.

anthropic-managed Claude Developer Platform · in the page build-with-claude/claude-models-on-google-cloud/anthropic-managed …its for Claude Models on Google Cloud (Anthropic managed). To request higher limits, contact your Anthropic account representative or [contact sales](https://claude.com/contact-sales). For how rate li… google-managed Claude Developer Platform · in the page build-with-claude/claude-models-on-google-cloud/google-managed …"`). Use it when you need data residency within a broad geography and higher availability than a single region. * **Regional:** Requests go only to the region you name, such as `"us-east5"` or `"europ… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …laude.com/docs/en/build-with-claude/overview). ### Supported feature highlights * [Messages API](https://platform.claude.com/docs/en/api/messages/create) * [Prompt caching](https://platform.claude.c… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …Bedrock:** Organizations in regulated industries that require FedRAMP High, IL4, IL5, or HIPAA-ready compliance, or that need AWS to be the sole data processor, should use [Claude in Amazon Bedrock](h… compaction-background Claude Developer Platform · in the page build-with-claude/compaction-background …p) with the compaction request taken off the conversation's path. The highlighted lines show where it differs from the loop, and the following list takes them in the order the program runs them. <Cod… compaction-keep-recent-turns Claude Developer Platform · in the page build-with-claude/compaction-keep-recent-turns …on-demand#compact-in-a-loop), changed to keep the last two turns. The highlighted lines show where it differs from the loop. <CodeGroup exclude="shell"> ```python Python from anthropic.types.beta… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …shold means more frequent compactions with smaller context windows. A higher threshold allows more context but risks hitting limits. <Tabs> <Tab title="cURL"> <Note> Compaction runs clien… effort Claude Developer Platform · in the page build-with-claude/effort …``` </CodeGroup> ## How effort works Most Claude models default to high effort, spending as many tokens as needed for excellent results; Claude Opus 5.5 and Claude Haiku 5.5 default to medium. You… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …---------------------------- | | `rerank-3` | 32,000 | Highest accuracy. Recommended for most applications. See the [rerank-3 blog post](https://blog.voyageai.com/2026/09/30/rerank-3/)… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …f 16,000 tokens or more and adjust to your latency and quality needs. Higher budgets allow more comprehensive reasoning, with diminishing returns that depend on the task, and at the cost of increased… fallback-credit Claude Developer Platform · in the page build-with-claude/fallback-credit …che_creation_input_tokens` is lower, and `cache_read_input_tokens` is higher by the same amount. A shift of zero means the token was honored but there was nothing to reprice, for example because the r… fast-mode Claude Developer Platform · in the page build-with-claude/fast-mode …e.com/docs/en/build-with-claude/fast-mode description: Get up to 2.5x higher output tokens per second from supported Claude models. featureMetadata: zdr: eligibility: eligible note: Excludes… files Claude Developer Platform · in the page build-with-claude/files …ls are limited to approximately 500 requests per minute. To request a higher limit, [contact sales](mailto:[email protected]). ## Next steps <CardGroup cols={3}> <Card title="PDF support" icon="… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …an incomplete tool use block, you'll need to retry the request with a higher `max_tokens` value to get the full tool use. <CodeGroup exclude="shell:cURL, shell:CLI"> <CodeGroupItem language="cU… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …platform.claude.com/docs/en/build-with-claude/effort) value such as `xhigh`. There is no hidden level above the ones on that page. This example sets effort at the top level of each request, which need… multilingual-support Claude Developer Platform · in the page build-with-claude/multilingual-support …results.md). The use of human translators for this evaluation ensures high-quality translations, particularly important for languages with fewer digital resources. </Note> *** ## Set the response la… overview Claude Developer Platform · in the page build-with-claude/overview …tool-use/advisor-tool) | Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation for long-horizon agentic workloads. | ZDR eligib… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …claude/pdf-support#process-document-batches): To process documents at high volume. * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview): To extract specific informa… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …can get even better performance by including 20+ diverse examples of high-quality answers. * Agentic tool use: Enhance performance for scenarios involving multiple tool calls and iterative code chang… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …em performance) This behavior is steerable. Although the model has a high success rate in parallel tool calling without prompting, you can boost this to about 100 percent or adjust the aggression lev… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …images, web applications, and detailed screenshots with substantially higher accuracy, often while using fewer output tokens, and is trained to use bash and crop tools to handle flipped, blurry, or no… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …observe: * Unsure which effort level to run, or latency and cost are higher than the task warrants: [Consider all effort levels](https://platform.claude.com/docs/en/build-with-claude/prompt-engineeri… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …est and fastest level. Use it for chat, short tool tasks, and simple, high-volume requests. In long agent prompts, the model is more likely to skip a search, stop early, or skip a check at this level.… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …ing off capability for faster speed and lower costs. Start with the `xhigh` effort level for coding and agentic use cases, and use a minimum of `high` effort for most intelligence-sensitive use cases.… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …r. * **Code review and bug-finding:** Claude Opus 5 reviews code with high precision and recall: it finds real bugs at a high rate per pass, and its additional findings are mostly real issues rather t… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …s default `medium` effort the model matched or beat Claude Opus 5 at `high` effort on such tasks, in fewer steps and with fewer tokens. It also sustains long-running autonomous work better than Claude… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …faster speed and lower costs. On Claude Sonnet 5, effort defaults to `high`, the same as on Claude Sonnet 4.6. For the hardest coding and agentic tasks, raise effort to `xhigh`. Experiment with other… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …than carrying over the setting you used on Claude Sonnet 5. Start at `high`, the default on the Claude API, unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …mage, and the rejection's reported rescale target fits them all. The highlighted lines are the only difference from the default-routing request. <CodeGroup> ```bash cURL curl --fail-with-body -s… streaming Claude Developer Platform · in the page build-with-claude/streaming …cs/en/api/errors) in the event stream. For example, during periods of high usage, you might receive an `overloaded_error`, which would normally correspond to an HTTP 529 in a non-streaming context: `… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …cted output format. This means: * Your input token count is slightly higher. * The injected prompt costs you tokens like any other system prompt. * Changing the `output_config.format` parameter will… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …refactor plan." }], "output_config": { "effort": "high", "task_budget": {"type": "tokens", "total": 64000} } }' ``` ```bash CLI ant beta:messages create --… thinking Claude Developer Platform · in the page build-with-claude/thinking …inking | 400 error | Up-front thinking off at `high` effort or below | 400 error | | Claude Haiku 5.5 | Adaptive thinking | Adaptive thinking… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …d at the greatest depth, with no constraint on thinking length. | | `xhigh` | Claude thinks more readily and at greater depth than at `high`, suited… thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …ffort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; combining it with effort `xhigh` or `max` returns a 400 error. On Claude Opus 5, this restriction is enforced on e… token-counting Claude Developer Platform · in the page build-with-claude/token-counting …pus 4.7. A prompt counts the same on all four, and roughly 30 percent higher than on models before Claude Opus 4.7 (the exact increase depends on the content). The token counting endpoint counts under… vision Claude Developer Platform · in the page build-with-claude/vision …ts-and-tools/tool-use/computer-use-tool#handle-coordinate-scaling-for-higher-resolutions) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#targets-and-c… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …d the crop (offset returned coordinates by the crop origin), or use a high-resolution-tier model. For [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), pages are raster… API usage primer for Claude Claude Developer Platform · in the page claude_api_primer …hits the `max_tokens` limit during tool use, retry the request with a higher `max_tokens` value. ### Handling the `pause_turn` stop reason When you use server tools such as web search, the API might… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …", capabilities: .init(samplingParams: false, effortLevels: [.low, .high]) ) ClaudeLanguageModel(name: model, auth: auth) ``` ### Effort Pin a Claude [effort level](https://platform.claude.com/doc… overview Claude Developer Platform · in the page cli-sdks-libraries/overview …laude Code, the Claude Agent SDK, and Claude Managed Agents work at a higher level, providing the agent loop, tool execution, and runtime. <CardGroup cols={3}> <Card title="Claude Code" href="https… java Claude Developer Platform · in the page cli-sdks-libraries/sdks/java …erialization/deserialization. It is compatible with version 2.13.4 or higher, but depends on version 2.19.4 by default. The SDK throws an exception if it detects an incompatible Jackson version at… php Claude Developer Platform · in the page cli-sdks-libraries/sdks/php …pic-ai/sdk" "guzzlehttp/guzzle:^7" ``` ## Requirements PHP 8.1.0 or higher. ## Usage This library uses named parameters to specify optional arguments. Parameters with a default value must be set b… Automatically handles tool execution loop Claude Developer Platform · in the page cli-sdks-libraries/sdks/ruby …er: ```bash bundle add anthropic ``` ## Requirements Ruby 3.2.0 or higher. ## Usage ```ruby anthropic = Anthropic::Client.new( api_key: ENV["ANTHROPIC_API_KEY"] # This is the default and can be… typescript Claude Developer Platform · in the page cli-sdks-libraries/sdks/typescript …[non-EOL](https://endoflife.date/nodejs)) versions. * Deno v1.28.0 or higher. * Bun 1.0 or later. * Cloudflare Workers. * Vercel Edge Runtime. * Jest 28 or greater with the `"node"` environment (`"jsd… home Claude Developer Platform · in the page home …g </HomeJourneyLink> <HomeJourneyLink icon="wifi-high" href="https://platform.claude.com/docs/en/build-with-claude/streaming"> Streaming </HomeJourneyLink>… intro Claude Developer Platform · in the page intro …l: https://platform.claude.com/docs/en/intro description: Claude is a highly performant, trustworthy, and intelligent AI platform built by Anthropic. Claude excels at tasks involving language, reasoni… First request Claude Developer Platform · in the page manage-claude/claude-code-analytics-api …ate records. ## Common use cases * **Executive dashboards:** Create high-level reports showing Claude Code impact on development velocity * **AI tool comparison:** Export metrics to compare Claude C… cmek-google-cloud-kms Claude Developer Platform · in the page manage-claude/cmek-google-cloud-kms … </Frame>… compliance-errors Claude Developer Platform · in the page manage-claude/compliance-errors …ys. Contact your Anthropic representative if your integration needs a higher limit. One 429 is different: on a very large session, the local session messages endpoint might return [Server busy readin…