526 pages for prompts.

strict-tool-use Claude Developer Platform · in the page agents-and-tools/tool-use/strict-tool-use …ool schemas are temporarily cached for up to 24 hours since last use. Prompts and responses are not retained beyond the API response. Strict tool use is HIPAA eligible, but **protected health informa… Beta Claude Developer Platform · in the page api/beta …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Messages Claude Developer Platform · in the page api/beta/messages …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Batches Claude Developer Platform · in the page api/beta/messages/batches …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Create a Message Batch Claude Developer Platform · in the page api/beta/messages/batches/create …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Count tokens in a Message Claude Developer Platform · in the page api/beta/messages/count_tokens …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Create a Message Claude Developer Platform · in the page api/beta/messages/create …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Apps Claude Developer Platform · in the page api/compliance/apps …session_id}/messages` Retrieve one remote session's transcript: user prompts, assistant responses, and tool calls and results. Thinking blocks and images are not included. Messages are returned olde… Sessions Claude Developer Platform · in the page api/compliance/apps/sessions …session_id}/messages` Retrieve one remote session's transcript: user prompts, assistant responses, and tool calls and results. Thinking blocks and images are not included. Messages are returned olde… Remote Claude Developer Platform · in the page api/compliance/apps/sessions/remote …session_id}/messages` Retrieve one remote session's transcript: user prompts, assistant responses, and tool calls and results. Thinking blocks and images are not included. Messages are returned olde… Messages Claude Developer Platform · in the page api/compliance/apps/sessions/remote/messages …session_id}/messages` Retrieve one remote session's transcript: user prompts, assistant responses, and tool calls and results. Thinking blocks and images are not included. Messages are returned olde… Retrieve remote session messages Claude Developer Platform · in the page api/compliance/apps/sessions/remote/messages/list …session_id}/messages` Retrieve one remote session's transcript: user prompts, assistant responses, and tool calls and results. Thinking blocks and images are not included. Messages are returned olde… Messages Claude Developer Platform · in the page api/messages …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Batches Claude Developer Platform · in the page api/messages/batches …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Create a Message Batch Claude Developer Platform · in the page api/messages/batches/create …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Count tokens in a Message Claude Developer Platform · in the page api/messages/count_tokens …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… Create a Message Claude Developer Platform · in the page api/messages/create …uch as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-ro… rate-limits Claude Developer Platform · in the page api/rate-limits …r rate limits, cache repeated content such as system instructions and prompts, large context documents, tool definitions, and conversation history; see [prompt caching](https://platform.claude.com/doc… cache-diagnostics Claude Developer Platform · in the page build-with-claude/cache-diagnostics …ant analyzing a large document. <document>...</document>"; const prompts = ["Summarize section 1.", "Now section 2.", "Now section 3."]; const messages: BetaMessageParam[] = []; let prev… claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …bject to Anthropic's data use terms. For deployments hosted on Azure, prompts and completions remain within Azure. Only usage metadata and content flagged by Anthropic's safety systems egress to Anthr… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …t/userguide/model-invocation-logging.html) that allows you to log the prompts and completions associated with your usage. Anthropic recommends that you log your activity on at least a 30-day rolling… claude-on-vertex-ai Claude Developer Platform · in the page build-with-claude/claude-on-vertex-ai …/docs/multimodal/request-response-logging) that allows you to log the prompts and completions associated with your usage. Anthropic recommends that you log your activity on at least a 30-day rolling… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …uests, run model inference, and store your workspace content (such as prompts, outputs, files, Skills, and batches). For workspaces created before September 18, 2026, 00:00 UTC, Anthropic might proces… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …want users to use one chat for a long period of time * Task-oriented prompts that require a lot of follow-up work (often tool use) that might exceed the context window ## How compaction works When… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …want users to use one chat for a long period of time * Task-oriented prompts that require a lot of follow-up work (often tool use) that might exceed the context window ## How compaction works When… context-editing Claude Developer Platform · in the page build-with-claude/context-editing ….input_tokens}" end ``` </Tab> </Tabs> #### Custom summary prompts You can provide a custom prompt for domain-specific needs. Your prompt should instruct Claude to wrap its summary in `<su… context-windows Claude Developer Platform · in the page build-with-claude/context-windows …er context window allows the model to handle more complex and lengthy prompts, but more context isn't automatically better. As token count grows, accuracy and recall degrade, a phenomenon known as *co… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …etrieval quality. When using the `input_type` parameter, special prompts are prepended to the input text prior to embedding. Specifically: > 📘 **Prompts associated with `input_type`** >… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …* Sending the empty response back won't help. 3. **Use continuation prompts as a last resort:** Only if these fixes don't resolve the issue. </Accordion> ### max\_tokens Claude stopped because it… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …pe": "string"}, "description": "Independent subtask prompts to run as parallel agents", } }, "required": ["subtasks"], }, } BASH_TOOL = {… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …t-engineering/claude-prompting-best-practices"> Writing effective prompts and system instructions. </Card> <Card title="Tool use with Claude" icon="wrench" href="https://platform.claude.com/d… overview Claude Developer Platform · in the page build-with-claude/overview …sending it to Claude, helping you make informed decisions about your prompts and usage. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexA… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …r upright orientation * Use logical page numbers (from PDF viewer) in prompts * Split large PDFs into chunks when needed * Enable prompt caching for repeated analysis ### Scale your implementation F… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …es your API usage by allowing resuming from specific prefixes in your prompts. This significantly reduces processing time and costs for repetitive tasks or prompts with consistent elements. <Note>… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …inking, and agentic systems. * **Migration considerations** last, for prompts moving from earlier generations. <Tip> For an overview of model capabilities, see the [models overview](https://platfor… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …estions, and execute. * **Make self-verification explicit in long-run prompts.** Separate, fresh-context verifier subagents tend to outperform self-critique. For long-running tasks, instruct: `Establi… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …ering/claude-prompting-best-practices). Your existing Claude Fable 5 prompts should perform well on Claude Fable 5.1 without changes, but a handful of behavioral differences are worth knowing about.… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …ry tasks. It performs well out of the box on existing Claude Opus 4.7 prompts. The following patterns cover the behaviors that most often require tuning. <Note> For the API parameter changes since… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …ic tasks. It performs well out of the box on existing Claude Opus 4.8 prompts. The following patterns cover the behaviors that most often require tuning. ## Capability improvements Compared with Cla… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …nds to finish the same task with fewer tokens. Existing Claude Opus 5 prompts should perform well without changes, and the patterns in [Prompting Claude Opus 5](https://platform.claude.com/docs/en/bui… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …tasks. It performs well out of the box on existing Claude Sonnet 4.6 prompts. The patterns in this guide cover the behaviors that most often require tuning. ## Response length and verbosity Claude… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …gineering/claude-prompting-best-practices). Existing Claude Sonnet 5 prompts should perform well without changes, and the patterns in [Prompting Claude Sonnet 5](https://platform.claude.com/docs/en/b… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …ing-a-raw-json-schema) for the updated API shape. ## Data retention Prompts and responses are processed with ZDR when using structured outputs. However, the JSON schema itself is temporarily cached… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …-with-claude/prompt-caching"> Reduce cost and latency on repeated prompts by caching prompt prefixes. </Card> </CardGroup> token-counting Claude Developer Platform · in the page build-with-claude/token-counting …o manage rate limits and costs, make model routing decisions, and fit prompts to a target length. featureMetadata: status: ga zdr: eligibility: eligible note: Excludes [Covered Models](htt… vision Claude Developer Platform · in the page build-with-claude/vision …pting-best-practices#long-context-prompting) improves results in text prompts, Claude works best when images come before text. Images placed after text or interpolated with text still perform well, bu… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …o manage rate limits and costs, make model routing decisions, and fit prompts to a target length. </Card> </CardGroup> using Claude Developer Platform · in the page cli-sdks-libraries/cli/using …--name "Researcher" --model '{id: claude-opus-5-5}' \ --system @./prompts/researcher.txt ``` Inside structured flag values, wrap the path in quotes. To send a PDF to the Messages API: ```bash an… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …to the Claude API; Apple is not in the request path and does not see prompts or responses. Usage is billed to your Anthropic account at [standard API pricing](https://platform.claude.com/docs/en/abou… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …rs, but one distinct difference is the handling of system / developer prompts. These two prompts can be put throughout a chat conversation via OpenAI. Since Anthropic only supports an initial system m…