50 pages for diff.

glossary Claude Developer Platform · in the page about-claude/glossary …odel can look back on and reference when generating new text. This is different from the large corpus of data the language model was trained on, and instead represents a "working memory" for the model… model-deprecations Claude Developer Platform · in the page about-claude/model-deprecations …own retirement schedules, so a model's lifecycle status and dates can differ. See the [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock#supported-models),… choosing-a-model Claude Developer Platform · in the page about-claude/models/choosing-a-model …The latest Opus model: breaking changes, new features, and behavior differences </Card> <Card title="What's new in Claude Opus 5" icon="sparkle" href="https://platform.claude.com/docs/en/models… Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page about-claude/models/migration-guide …own workloads. Token counts are roughly unchanged; per-token pricing differs. ### Migrating to Claude Mythos 5 and Claude Fable 5 from Claude Opus 4.8 <Note> If your code is on Claude Opus 4.7 or… model-ids-and-versions Claude Developer Platform · in the page about-claude/models/model-ids-and-versions …an updated version is available, it ships under a new model ID. This differs from the dateless aliases that exist on the Claude API for earlier models. An alias such as `claude-sonnet-4-5` is a conve… optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …the duration instead. On Claude Fable 5.1 the cheapest setting is a different one. Its [cache read](https://platform.claude.com/docs/en/about-claude/pricing#prompt-caching) costs 0.025x the input pr… content-moderation Claude Developer Platform · in the page about-claude/use-case-guides/content-moderation …atile tool for comprehensive content moderation in environments where different media types need to be evaluated together. </Accordion> </AccordionGroup> <Note> All Claude models are trained with… customer-support-chat Claude Developer Platform · in the page about-claude/use-case-guides/customer-support-chat …into unique tasks Customer support chat is a collection of multiple different tasks, from question answering to information retrieval to taking action on requests, wrapped up in a single customer in… Create the full URL from the GitHub repository Claude Developer Platform · in the page about-claude/use-case-guides/legal-summarization …ct summary for any given document. Without clear direction, it can be difficult for Claude to determine which details to include. To achieve optimal results, identify the specific information you want… overview Claude Developer Platform · in the page about-claude/use-case-guides/overview …> ## Choosing a build path The three paths for building with Claude differ in how much control you keep and how much of the implementation you offload to Anthropic. The [Messages API](https://platfo… Create an instance of the Claude API client Claude Developer Platform · in the page about-claude/use-case-guides/ticket-routing …te tickets in multiple languages. Measure the routing accuracy across different languages, aiming for no more than a 5–10% drop in accuracy for non-primary languages. </Accordion> <Accordion titl… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/best-practices …ml description: Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes. ``` Avoid vague descriptions like the… claude-api-skill Claude Developer Platform · in the page agents-and-tools/agent-skills/claude-api-skill …iggering, subagent, and instruction-following prompts that may behave differently on the target model * **Silent default handling**, opting back into thinking summarization (`thinking.display: "summar… enterprise Claude Developer Platform · in the page agents-and-tools/agent-skills/enterprise …consolidating narrow Skills into broader ones or routing requests to different Skill sets based on task type. ### Start specific, consolidate later Encourage teams to start with narrow, workflow-sp… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/overview …upfront. Skills can contain three types of content, each loaded at a different time: ### Level 1: Metadata (always loaded) The Skill's YAML frontmatter provides discovery information: ```yaml ---… quickstart Claude Developer Platform · in the page agents-and-tools/agent-skills/quickstart …execution tool version satisfies the Skills requirement. If you use a different version, use the tool `type` listed on the code execution tool page. </Note> When you make this request, Claude automat… concepts Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/concepts …/mcp-tunnels/overview) documentation. Several components appear under different names in configuration files, container images, and prose; the following tables give one canonical name for each and lis… deploy-helm Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/deploy-helm …s ServiceAccount token for the setup component. To use a token from a different identity provider (such as [SPIFFE](https://platform.claude.com/docs/en/manage-claude/wif-providers/spiffe), Vault, or a… troubleshooting Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/troubleshooting …s/en/agents-and-tools/mcp-tunnels/overview#network-requirements) is a different hop.) If the proxy logs `IP validation failed: <ip> is not a private address`, the upstream hostname resolved outside t… advisor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/advisor-tool …are not rolled into the top-level totals because they are billed at a different rate. Iterations with `type: "advisor_message"` are billed at the advisor model's rates, and iterations with `type: "mes… browser-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/browser-use-tool ….claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use); the difference is that you run the blocks in order rather than concurrently. Here Claude clicks the search box it found earlier, types… build-a-tool-using-agent Claude Developer Platform · in the page agents-and-tools/tool-use/build-a-tool-using-agent …w which 10 people to prioritize. ``` The `is_error` flag is the only difference from a successful result. Claude sees the flag and the error text, and responds accordingly. See [Handle tool calls](ht… code-execution-tool Claude Developer Platform · in the page agents-and-tools/tool-use/code-execution-tool …ution_20260521` is the same runtime as `code_execution_20260120`. The difference is that the tool description tells Claude about the 90-second wall-clock limit on each Python cell in programmatic tool… computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …ude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use) with one difference: you run the blocks in order rather than concurrently. A response with a three-action batch looks like this: ```json… define-tools Claude Developer Platform · in the page agents-and-tools/tool-use/define-tools …rted | On models that support it, the highlighted lines are the only difference from a standard tool use request: <CodeGroup> ```bash cURL curl -sS https://api.anthropic.com/v1/messages \ -H… handle-tool-calls Claude Developer Platform · in the page agents-and-tools/tool-use/handle-tool-calls …u need custom control over tool execution. </Note> Claude's response differs based on whether it uses a [client or server tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#… how-tool-use-works Claude Developer Platform · in the page agents-and-tools/tool-use/how-tool-use-works …terface: define the schema, handle the callback, return a result. The difference is that the caller on the other side is a language model choosing which function to call based on the conversation. ##… manage-tool-context Claude Developer Platform · in the page agents-and-tools/tool-use/manage-tool-context …context before the task is finished. Four approaches address this at different points in the pipeline. ## The four approaches Each approach targets a different source of context pressure. Pick the… memory-tool Claude Developer Platform · in the page agents-and-tools/tool-use/memory-tool …aude reads whatever text your tool result contains, so you can return different strings if your application needs to. ### view Shows directory contents or file contents with optional line ranges: `… overview Claude Developer Platform · in the page agents-and-tools/tool-use/overview …-and-tools/tool-use/handle-tool-calls). ## How tool use works Tools differ primarily by where the code executes. **Client tools** (including user-defined tools and tools with Anthropic-defined schem… server-tools Claude Developer Platform · in the page agents-and-tools/tool-use/server-tools …in. Check `stop_reason` on each response and continue until you get a different stop reason, capping the number of continuations as you would any retry loop. For the other `stop_reason` values and ge… text-editor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/text-editor-tool …needed, especially if you're working with multiple files or files in different directories. **Less helpful prompt:** "Review my helper file" **Better prompt:** "Can you check my utils/helpe… tool-reference Claude Developer Platform · in the page agents-and-tools/tool-use/tool-reference …oading` on the entry, or enabled members whose `defer_loading` values differ (set it per member in `configs`, all to the same value). * A code execution caller in `allowed_callers` (no [programmatic t… Log at info level Claude Developer Platform · in the page agents-and-tools/tool-use/tool-runner …propriately. However, you might want to detect errors and handle them differently, for example, to stop execution early or implement custom error handling. In the Python and TypeScript SDKs, use the… tool-search-tool Claude Developer Platform · in the page agents-and-tools/tool-use/tool-search-tool …_name", re.IGNORECASE)`. 3. Matching is case-insensitive, so casing differences aren't the problem. 4. Claude uses broad patterns such as `".*weather.*"`, not exact matches. **Tip:** Add common… troubleshooting-tool-use Claude Developer Platform · in the page agents-and-tools/tool-use/troubleshooting-tool-use …Description ambiguity | Sharpen descriptions. Differentiate tools by WHEN to use them, not only WHAT they do. See [Define tools](https://platform.claude.com/docs/en/agents-and-… web-fetch-tool Claude Developer Platform · in the page agents-and-tools/tool-use/web-fetch-tool …ior is managed automatically and may change over time to optimize for different content types and usage patterns. To fetch fresh content, set `"use_cache": false` (see [Cache bypass](https://platform.… Beta Claude Developer Platform · in the page api/beta …ompt-caching#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/… beta-headers Claude Developer Platform · in the page api/beta-headers …ve breaking changes with notice * Be deprecated or removed * Have different rate limits or pricing * Not be available in all regions </Warning> ### Multiple beta features To use multiple beta… Memory Stores Claude Developer Platform · in the page api/beta/memory_stores …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Memories Claude Developer Platform · in the page api/beta/memory_stores/memories …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Create a memory Claude Developer Platform · in the page api/beta/memory_stores/memories/create …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Delete a memory Claude Developer Platform · in the page api/beta/memory_stores/memories/delete …cimal characters. Omit it to delete unconditionally. If the hashes differ, the request fails with HTTP status 409 and nothing is deleted. ## Headers - `"anthropic-beta": optional array of Anthrop… List memories Claude Developer Platform · in the page api/beta/memory_stores/memories/list …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Retrieve a memory Claude Developer Platform · in the page api/beta/memory_stores/memories/retrieve …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Update a memory Claude Developer Platform · in the page api/beta/memory_stores/memories/update …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Memory Versions Claude Developer Platform · in the page api/beta/memory_stores/memory_versions …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… List memory versions Claude Developer Platform · in the page api/beta/memory_stores/memory_versions/list …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Retrieve a memory version Claude Developer Platform · in the page api/beta/memory_stores/memory_versions/retrieve …es` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps… Messages Claude Developer Platform · in the page api/beta/messages …ompt-caching#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/…