740 pages for term.

context-windows Claude Developer Platform · in the page build-with-claude/context-windows …s://platform.claude.com/docs/en/build-with-claude/thinking), Claude determines its thinking allocation dynamically, so thinking token usage varies from request to request. Whether thinking blocks fro… effort Claude Developer Platform · in the page build-with-claude/effort …-steering-and-cost"> Understand adaptive thinking, where Claude determines when and how much to think, and steer it with effort and prompting. </Card> <Card title="Thinking" icon="brain" href… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …example, you can send an HTTP request through the `curl` command in a terminal: ```bash cURL curl https://ai.mongodb.com/v1/embeddings \ -H "Content-Type: application/json" \ -H "Authorization: B… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …in a single assistant turn, reasoning about each tool result before determining what to do next. For the concept, the turn structure, and how it behaves on adaptive-thinking models, see [interleaved t… fallback-credit Claude Developer Platform · in the page build-with-claude/fallback-credit …claude/prompt-caching) explains cache reads and cache writes if those terms are new. ## The basic flow <Steps> <Step title="Opt in with the beta header"> Send the request that may be refused w… files Claude Developer Platform · in the page build-with-claude/files …your documents. </Card> <Card title="Code execution tool" icon="terminal" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool"> Run Python and Bash code i… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …) with `stop_reason: "end_turn"`. This typically occurs when Claude determines that the assistant turn is complete, particularly after tool results. **Common causes:** * Adding text blocks immed… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …::CLOCK_MONOTONIC) < deadline begin Process.kill("-TERM", wait_thr.pid) rescue Errno::ESRCH end unless wait_thr.join(2) begin Process.k… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …orm.claude.com/docs/en/agents-and-tools/mcp-connector#data-retention) terms. ## When to use a mid-conversation system message [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/p… overview Claude Developer Platform · in the page build-with-claude/overview …uild-with-claude/thinking) | Let Claude dynamically determine when and how much to think. The only thinking mode on Claude 4.7 and later models. Use the `effort` parameter to control t… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …roperty of newer Claude models that guards against distillation. It determines whether the model can use a thinking block that you send back from an earlier turn. Starting with Claude Fable 5.1, when… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …} ], "messages": [{ "role": "user", "content": "What are the key terms?" }] } ``` ### What stays the same Automatic caching uses the same underlying caching infrastructure. Pricing, minimum tok… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …hinking) (`thinking: {type: "adaptive"}`), where Claude dynamically determines when and how much to think. On Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, and Claude Opus 5.5,… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …rforms well when given complex, multithreaded requests and asked to determine next steps. * **Delegation and collaboration.** Claude Fable 5 is significantly more dependable at dispatching and sustain… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …beta): ```text wrap Only you see that command's output — the user's terminal shows at most a few lines of it. If the user needs to read any of it, put it in your reply. ``` ## Batch independent too… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …t as thoroughly, identify the bugs, and then not report findings it determines to be below your stated bar. This can show up as the model doing the same depth of investigation but converting fewer inv… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …ive explicit guidance on which scenarios warrant delegation, or set deterministic caps on how many agents can be launched. For example: ```text wrap Delegate to a subagent only for large tasks that a… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …re answering, consider removing them for Claude Opus 5.5. The model determines how much to think, and the [effort level](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompt… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …t as thoroughly, identify the bugs, and then not report findings it determines to be below your stated bar. This can show up as the model doing the same depth of investigation but converting fewer inv… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …ompeting AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category.… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …se successfully. </Card> <Card title="Code execution tool" icon="terminal" href="https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool"> Run Python and Bash code i… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …form.claude.com/docs/en/build-with-claude/thinking"> Let Claude determine when and how much to use extended thinking. </Card> <Card title="Compaction overview" icon="arrows-clockwise" href="h… thinking Claude Developer Platform · in the page build-with-claude/thinking …nswering: it restates what is being asked, tries approaches, checks intermediate results, and abandons paths that do not hold up. That up-front thinking arrives in `thinking` content blocks ahead of t… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …Claude's thinking is adaptive: the model evaluates each request and determines whether to think and how much. You set an intent, optionally specify the effort, and the model allocates reasoning where… thinking-tool-workflows Claude Developer Platform · in the page build-with-claude/thinking-tool-workflows …think after receiving each tool result, allowing it to reason about intermediate results before continuing. ```text User: "What's the total revenue if we sold 150 units at $50 each,… thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …is is normal in adaptive mode: Claude skips thinking on requests it determines are simple enough to answer directly. If you want thinking more often or more deeply, raise `effort` or steer with promp… token-counting Claude Developer Platform · in the page build-with-claude/token-counting …managed): ga Microsoft Foundry: ga --- Token counting lets you determine the number of tokens in a message before you send it to Claude. This helps you make informed decisions about your prompts… vision Claude Developer Platform · in the page build-with-claude/vision …numbers of small objects. * **AI-generated images:** Claude cannot determine whether an image is AI-generated and might be incorrect if asked. Do not rely on it to detect fake or synthetic images. *… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …r nearly all photos and screenshots, the visual token limit is what determines the final size. The edge limit takes over only for elongated images such as panoramas or tall phone screenshots. Compute… API usage primer for Claude Claude Developer Platform · in the page claude_api_primer …ld-with-claude/thinking) (`thinking: {"type": "adaptive"}`): Claude determines when and how much to think, and you steer thinking depth with the [`effort`](https://platform.claude.com/docs/en/build-wi… apply Claude Developer Platform · in the page cli-sdks-libraries/cli/apply …agent from its path, here the `agents/` directory. In an interactive terminal, `ant apply` prints the plan and waits for your approval: ```text Output wrap First apply ./claude-lock.json does not e… On a remote host without a browser: Claude Developer Platform · in the page cli-sdks-libraries/cli/authentication …to print the authorize URL and paste the returned code back into the terminal. ```bash CLI ant auth login # On a remote host without a browser: ant auth login --no-browser # Bind to a specific wor… quickstart Claude Developer Platform · in the page cli-sdks-libraries/cli/quickstart …e API. --- The `ant` CLI provides access to the Claude API from your terminal. Every API resource is exposed as a subcommand, with output formatting, response filtering, and YAML or JSON file input.… scripting Claude Developer Platform · in the page cli-sdks-libraries/cli/scripting …ides the interactive explorer that list commands open by default in a terminal: ```bash ant beta:sessions:events list \ --session-id session_01JZCh78XvmxJjiXVy3oSi7K \ --transform… sessions-connect Claude Developer Platform · in the page cli-sdks-libraries/cli/sessions-connect --- title: Connect to a Managed Agents session from your terminal url: https://platform.claude.com/docs/en/cli-sdks-libraries/cli/sessions-connect description: Attach the ant CLI to a Claude Managed A… using Claude Developer Platform · in the page cli-sdks-libraries/cli/using …/cli-sdks-libraries/cli/using#interactive-explorer) when writing to a terminal, and to pretty-printed JSON when piped. Override either default with `--format`: ```bash ant models retrieve --model-id… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …s an available credit balance or an active billing method. Your app determines when to use Claude and when to use Apple's on-device model: pass whichever model you want to each session. <Note> **Be… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …to test and compare model capabilities, and is not considered a long-term or production-ready solution for most use cases. Although it is intended to remain fully functional and not have breaking cha… java Claude Developer Platform · in the page cli-sdks-libraries/sdks/java …ou define JSON schemas for tools, and the model uses the schemas to determine when and how to use these tools. The tool use feature supports a "strict" mode that guarantees that the JSON output from… For Amazon Bedrock support Claude Developer Platform · in the page cli-sdks-libraries/sdks/python …n't expected to impact the vast majority of users in practice. ### Determining the installed version If you've upgraded to the latest version but aren't seeing new features you were expecting, your… Automatically handles tool execution loop Claude Developer Platform · in the page cli-sdks-libraries/sdks/ruby …aw `IO` descriptor, but this disables retries, as the library can't determine whether the descriptor is a file or pipe (which cannot be rewound). ## Sorbet This library provides comprehensive [RBI](… get-api-key Claude Developer Platform · in the page get-api-key …hoose a key type When you create a key, you choose its type, which determines what the key can do, where it works, and when it stops working. A **personal key** acts as you, and stops working if you… get-started Claude Developer Platform · in the page get-started …ind the latest developments in renewable energy:\n\n## General Search Terms\n- \"Renewable energy news 2025\"\n- ..." } ], "stop_reason": "end_turn", "stop_se… home Claude Developer Platform · in the page home …ge conversation state, and write your own tool loop." pictogram="code-terminal"> <HomeCardLink icon="play" href="https://platform.claude.com/docs/en/get-started"> Quickstart… access-transparency Claude Developer Platform · in the page manage-claude/access-transparency …equest and is not self-serve. For eligibility, refer to your contract terms or contact your Anthropic account representative. </Note> ## How Access Transparency works Anthropic personnel access cust… access-transparency-log Claude Developer Platform · in the page manage-claude/access-transparency-log …curity, privacy, or regulatory requirement. You are responsible for determining whether it fits your own obligations. </Note> ## How the transparency log works A transparency log is a technique for… api-and-data-retention Claude Developer Platform · in the page manage-claude/api-and-data-retention …Commercial organization (an organization under Anthropic's Commercial Terms of Service, as distinct from a consumer Claude account). If metrics logging is enabled in Claude Code, productivity data suc… authentication Claude Developer Platform · in the page manage-claude/authentication …. ### Key types When you create a key, you choose its type, which determines what the key can do, where it works, and when it stops working: | Key type | Acts as… First request Claude Developer Platform · in the page manage-claude/claude-code-analytics-api …only usage authenticated against your Claude Console organization * **terminal\_type:** Type of terminal or environment where Claude Code was used (for example, `vscode`, `iTerm.app`, `tmux`) #### Co… cmek Claude Developer Platform · in the page manage-claude/cmek …In organizations with HIPAA readiness, an Owner must first accept the terms for using them. * Claude Code cannot [publish artifacts](https://code.claude.com/docs/en/artifacts#availability). However, a…