1,040 pages for comm.

Users Claude Developer Platform · in the page api/organization/analytics/users …the window is the exact count of distinct creations in it. - `commit_count: number` Number of commits made via Claude Code - `distinct_session_count: number or null` N… List User Activity Claude Developer Platform · in the page api/organization/analytics/users/list …the window is the exact count of distinct creations in it. - `commit_count: number` Number of commits made via Claude Code - `distinct_session_count: number or null` N… overview Claude Developer Platform · in the page api/overview …e for feature availability and timing. * **Best for:** Existing cloud commitments, specific compliance requirements, consolidated cloud billing | Platform | P… rate-limits Claude Developer Platform · in the page api/rate-limits …Limits are designed to prevent API abuse, while minimizing impact on common customer usage patterns. * Limits are defined by **usage tier**. Organizations are placed on a tier automatically based on… service-tiers Claude Developer Platform · in the page api/service-tiers …vice tiers are legacy. </Warning> <Warning> Priority Tier capacity commitments are no longer available for purchase. Organizations with an existing commitment can continue to use Priority Tier thro… versioning Claude Developer Platform · in the page api/versioning …Anthropic will not break your usage. ## Version history Anthropic recommends using the latest API version whenever possible. * `2026-10-21` * [Migrating to API version 2026-10-21](https://platfo… Message Batches API Claude Developer Platform · in the page build-with-claude/batch-processing …Console. Because of the potentially large size of the results, it’s recommended to [stream results](https://platform.claude.com/docs/en/api/messages/batches/results) back rather than download them all… cache-diagnostics Claude Developer Platform · in the page build-with-claude/cache-diagnostics …nguage="cURL"> This workflow needs more logic than a single shell command. Use the Anthropic SDK to run the loop. Each turn sends the same HTTP request as in [Basic usage](https://platform.claude.… claude-in-amazon-bedrock Claude Developer Platform · in the page build-with-claude/claude-in-amazon-bedrock …at best fits your security requirements. ### Bedrock service role (recommended) Use a Bedrock service role with AWS-managed keys for the most secure, long-lived access: <Steps> <Step title="Admin… claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …| | Recommended for | Most workloads | [Access to features or models not yet hosted on… anthropic-managed Claude Developer Platform · in the page build-with-claude/claude-models-on-google-cloud/anthropic-managed …me, entity type, country, and intended use. 5. Accept Anthropic’s Commercial Terms of Service and Usage Policy. The contact address is used only for setup and service notices. For how people… google-managed Claude Developer Platform · in the page build-with-claude/claude-models-on-google-cloud/google-managed …anaged) can get its token from `gcloud auth print-access-token`. That command uses the gcloud CLI’s own login, not Application Default Credentials, so run `gcloud auth login` or `gcloud init` before y… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …ply to those requests. To install an SDK for these models, use the commands in [Install an SDK for accessing Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …rks Claude models run on Anthropic-managed infrastructure. This is a commercial integration for billing and access through AWS. Anthropic is the data processor for inference inputs and outputs. AWS p… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …a), Microsoft Foundry (beta) <Tip> Server-side compaction is the recommended strategy for managing context in long-running conversations and agentic workflows. It handles context management automat… compaction-on-demand Claude Developer Platform · in the page build-with-claude/compaction-on-demand …nguage="cURL"> This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it. </CodeGroupItem> <CodeGroupItem language="CLI"> This workflow needs more logic… compaction-thinking-blocks Claude Developer Platform · in the page build-with-claude/compaction-thinking-blocks …nguage="cURL"> This workflow needs more logic than a single shell command. Use the Anthropic SDK to run it. </CodeGroupItem> <CodeGroupItem language="CLI"> This workflow needs more logic… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …fore continuing. Continuing # needs more logic than a one-off shell command. Single paused request: curl https://api.anthropic.com/v1/messages \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "an… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …{ "role": "user", "content": "Create a simple command line calculator app using Python" } ], "tools": [ { "type": "text_editor_20250728",… effort Claude Developer Platform · in the page build-with-claude/effort …ng-and-effort). Where adaptive thinking is available, effort is the recommended way to control thinking depth. </Tip> ## Set the effort level Set `output_config.effort` on the request. The following… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …ications, and how to use embedding models for tasks such as search, recommendations, and anomaly detection. --- ## Before implementing embeddings When selecting an embeddings provider, there are sev… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …ort it and reject requests that use it, returning a 400 error. * Recommended alternative: [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost) * M… fallback-credit Claude Developer Platform · in the page build-with-claude/fallback-credit …nguage="cURL"> 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. </CodeGroupItem>… fast-mode Claude Developer Platform · in the page build-with-claude/fast-mode …Priority Tier](https://platform.claude.com/docs/en/api/service-tiers) commitment. ## Pricing Fast mode is priced at a multiplier on standard rates across the full context window, including requests… files Claude Developer Platform · in the page build-with-claude/files …-H "anthropic-version: 2026-10-21" ``` ```bash CLI # List commands auto-paginate, so --max-items limits the total ant files list --max-items 10 ``` ```python Python client = anthr… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …tokens": 50 } } ``` ## Stop reason values ### end\_turn The most common stop reason. Indicates Claude completed its response naturally. <CodeGroup> ```bash cURL curl https://api.anthropic.co… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …"description": "How it was verified (file, line, or command output)", }, "severity": { "type": "stri… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …sh." } ] ``` Phrase the system content as context rather than as a command that overrides the user. State the fact (“new input arrived from the user: X,” “the remaining token budget is now Y”) and… multilingual-support Claude Developer Platform · in the page build-with-claude/multilingual-support …tion for optimal results. 3. **Consider cultural context:** Effective communication often requires cultural and regional awareness beyond pure translation. Also follow the general guidance in [Prompt… overview Claude Developer Platform · in the page build-with-claude/overview …| Lets Claude request shell commands, which run in a bash session that keeps its state between commands. | | [Code execu… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …"role": "user", "content": "What is the greatest common divisor of 1071 and 462?" } ] }' ``` ```bash CLI ant beta:messages create --beta thinking-binding-… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …ked with analyzing literary works. Your goal is to provide insightful commentary on themes, characters, and writing style.", "messages": [ { "role": "user", "content"… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …l report and competitor analysis. Identify strategic advantages and recommend Q3 focus areas. ``` </Accordion> * **Ground responses in quotes:** For long document tasks, ask Claude to quote rel… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …ching and sustaining parallel subagents, and reliably manages ongoing communication with long-running subagents and peer agents. Beyond these specific improvements, Claude Fable 5 is generally more c… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …e-in-compaction-summaries) * Unrequested fixes or extensions, or more committed test files than the task called for: [Keep changes and tests to what the task asks for](https://platform.claude.com/docs… Finishing work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-2 …he following: ### Modify your harness An effective way to encourage communication is to count consecutive tool-calling steps that give the user nothing to read: no `text` block and no `thinking` blo… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …it done: the project's tests, type-checker, or build, or the changed command itself. A syntax-only check, or a check command that failed to start, does not count; if all that is missing is the projec… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …your prompt to prevent them. Positive examples showing how Claude can communicate with the appropriate level of concision tend to be more effective than negative examples or instructions that tell the… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …from a prior model, re-run an effort sweep on your own evals. See [recommended effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#recommended-effort-levels-for-claude-opus-5)… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …nd documents it produces need less editing before you share them. * **Communication:** Its reports on agentic work, both the updates while it works and the summary when it finishes, say plainly what i… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …your prompt to prevent them. Positive examples showing how Claude can communicate with the appropriate level of concision tend to be more effective than negative examples or instructions that tell the… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …d on each line, keep the last run of values separated only by spaces, commas, or line breaks. Check that the result has the fields you expect, and retry once if it doesn’t. In testing, this made nearl… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …the API retries a declined request on the fallback model Anthropic recommends for its refusal category. For categories with no recommended fallback, the refusal stands. Claude Haiku 5.5 has no server… search-results Claude Developer Platform · in the page build-with-claude/search-results …earch logic in your application, which needs more than a single shell command. Use the Anthropic SDK for the full flow. For the raw request shape of a tool conversation with search results, see [Combi… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …nguage="cURL"> 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. </CodeGroupItem>… streaming Claude Developer Platform · in the page build-with-claude/streaming …"role": "user", "content": "What is the greatest common divisor of 1071 and 462?" } ] }' ``` ```bash CLI ant messages create --stream --format jsonl \… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …https://docs.pydantic.dev/) model to `client.messages.parse()`, the recommended method, as `output_format`. The SDK transforms the model’s schema, sends it as `output_config.format`, validates the res… task-budgets Claude Developer Platform · in the page build-with-claude/task-budgets …till counts earlier turns’ history while it remains in the context. A common case is a follow-up after Claude has ended its turn, for example because the budget ran out: ```json { "role": "user", "co… thinking Claude Developer Platform · in the page build-with-claude/thinking …"role": "user", "content": "What is the greatest common divisor of 1071 and 462?" } ] }' ``` ```bash CLI ant messages create \ --model claude-opus-5-5… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …on which level to choose for a given workload, including per-model recommendations, see [When to adjust the effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort#when-to-adju…