@font-face {
  font-family: 'Styrene Display';
  src: url('https://www-cdn.anthropic.com/e8f9c8ca51b03efb6315db351446fc972ab15abe/StyreneA-Medium-Web.woff2') format('woff2');
  font-weight: 500;
  font-style: normal;
  font-stretch: normal;
}

@font-face {
  font-family: 'Styrene Display';
  src: url('https://www-cdn.anthropic.com/e8f9c8ca51b03efb6315db351446fc972ab15abe/StyreneA-Medium-Web.woff2') format('woff2');
  font-weight: 600;
  font-style: normal;
  font-stretch: normal;
}

@font-face {
  font-family: 'Styrene';
  src: url('https://www-cdn.anthropic.com/6f87b6d99aefde021ac24f21295bf9e70f71472f/StyreneBLC-Regular.woff2') format('woff2');
  font-weight: 400;
  font-style: normal;
  font-stretch: normal;
}


@font-face {
  font-family: 'Styrene';
  src: url('https://www-cdn.anthropic.com/6f87b6d99aefde021ac24f21295bf9e70f71472f/StyreneBLC-Regular.woff2') format('woff2');
  font-weight: 500;
  font-style: normal;
  font-stretch: normal;
}
 
 @font-face {
  font-family: 'Styrene';
  src: url('https://www-cdn.anthropic.com/3611e9e4aaaf466dbd47e2686f561e7de694cb6c/StyreneBLC-Medium.woff2') format('woff2');
  font-weight: 600;
  font-style: normal;
  font-stretch: normal;
}
 

@font-face {
  font-family: 'Tiempos';
  src: url('https://www-cdn.anthropic.com/c3e09cefbfeb4e5eaca56b7bc8b9a1aa1aeda025/TiemposText-Regular.woff2') format('woff2');
  font-weight: 400;
  font-style: normal;
  font-stretch: normal;
}

@font-face {
  font-family: 'Tiempos';
  src: url('https://www-cdn.anthropic.com/b198ca4e31a323b2abb84b3eeeb1eed1f471afa0/TiemposText-Medium.woff2') format('woff2');
  font-weight: 500;
  font-style: normal;
  font-stretch: normal;
}

@font-face {
  font-family: 'Tiempos';
  src: url('https://www-cdn.anthropic.com/b198ca4e31a323b2abb84b3eeeb1eed1f471afa0/TiemposText-Medium.woff2') format('woff2');
  font-weight: 600;
  font-style: normal;
  font-stretch: normal;
}

@font-face {
  font-family: 'Copernicus';
  src: url('https://www-cdn.anthropic.com/db30aec85c7615f4a4d3e23c0c941674ea67f8f5/Copernicus-Book.woff2') format('woff2');
  font-weight: 300; /* Assuming 300 is the lightest available weight */
  font-style: normal;
}

#home-header {
  font-family: 'Copernicus', sans-serif;
  font-weight: 300 !important;
  font-size: 50px;
  line-height: 1.2;
  margin-bottom: 1rem;
  color: black;
  display: flex;
  align-items: baseline;
  justify-content: center;
  flex-wrap: nowrap;
}

.build-with {
  font-family: 'Copernicus', sans-serif;
  white-space: nowrap;
  letter-spacing: -0.02em;
}

.claude-wordmark-wrapper {
  display: inline-flex;
  align-items: baseline;
  margin-left: 10px; /* Space between "Build with" and the wordmark */
}

.claude-wordmark {
  height: 40px; /* Adjust this value to match your desired size */
  width: auto;
  position: relative;
}

.dark #home-header {
  color: white;
}

.description-text {
  color: black;
}

.dark .description-text {
  color: white;
}

.dark .claude-wordmark {
  filter: invert(1);
}

:root {
  --bg-color: #F0EFEA;
}

.dark {
  --bg-color: #2B2B2B;
}

#background-div {
  background-color: var(--bg-color);
  transition: background-color 0.3s ease;
}

body, input, #category-select, .dropdown-item, #table-of-contents {
  font-family: 'Styrene', sans-serif;
}

.eyebrow {
  font-family: 'Styrene Display', sans-serif;
  text-transform: uppercase;
  letter-spacing: .02rem;
}

#content-container {
  font-family: 'Tiempos', serif;
}

#content-container h1, #content-container h2, #content-container h3, #content-container h4, #content-container h5, #content-container h6 {
  font-family: 'Styrene Display', sans-serif;
}


#content-container p {
  font-size: 1rem;
  line-height: 1.65rem;
}

.font-extrabold {
  font-weight: 600 !important;
}

.wide-table {
  width: 100%;
  overflow-x: auto;
}

.wide-table table {
  width: 175%;
  margin-bottom: 0;
}

/* Prompt Library */
#prompt-library-container {
  margin: 4rem auto;
  max-width: 48rem;
  padding-left: 1.25rem;
  padding-right: 1.25rem;
}

.prompt-library-title {
  font-size: 24px;
  text-align: center;
  font-weight: 700;
  color: #1f2937;
}

.dark .prompt-library-title {
  color: #e5e7eb;
}

.prompt-library-description {
  margin-top: 1rem;
  text-align: center;
}

.main-content {
  margin-bottom: 10rem;
  max-width: 64rem;
  margin-left: auto;
  margin-right: auto;
  padding-left: 1.25rem;
  padding-right: 1.25rem;
}

.prompt-controllers {
  display: flex;
  gap: 0.5rem;
}

.prompt-search-container {
  position: relative;
  flex: 1 1 0%;
}

.prompt-search-icon-container {
  display: flex;
  position: absolute;
  top: 0;
  bottom: 0;
  left: 0;
  align-items: center;
  padding-left: 0.75rem;
}

.prompt-search-icon {
  margin-left: 0.25rem;
  margin-right: 0.75rem;
  flex: none;
  width: 1rem;
  height: 1rem;
  background-color: #6b7280;
  mask-image: url(https://mintlify.b-cdn.net/v6.5.1/solid/magnifying-glass.svg);
  mask-repeat: no-repeat;
  mask-position: center center;
}

input.prompt-search-bar {
  display: block;
  height: 2.5rem;
  padding-left: 2.5rem;
  border-radius: 0.75rem;
  border-width: 1px;
  background-color: #ffffff;
  width: 100%;
  color: #111827;
  box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
}

.dark input.prompt-search-bar {
  color: #ffffff;
  background-color: rgb(var(--background-dark));
  border-color: #d1d5db1a;
}

input.prompt-search-bar:focus {
  outline-color: rgb(var(--primary));
}

.dark input.prompt-search-bar:focus {
  outline-color: rgb(var(--primary-light));
}

.dark .prompt-search-icon {
  background-color: #ffffff80;
}

#category-select {
  padding-left: 1rem;
  padding-right: 2.5rem;
  height: 2.5rem;
  display: flex;
  align-items: center;
  border-radius: 0.75rem;
  border-width: 1px;
  color: #111827;
  background-color: #ffffff;
  cursor: pointer;
  box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
  white-space: nowrap;
}

.dark #category-select {
  background-color: rgb(var(--background-dark));
  border-color: #d1d5db1a;
  color: #ffffff;
}

#category-select:hover {
  background-color: #f9fafb;
}

.dark #category-select:hover {
  background-color: #ffffff0d;
}

#category-select:focus {
  outline-color: rgb(var(--primary));
}

.dark #category-select:focus {
  outline-color: rgb(var(--primary-light));
}

#categories-dropdown {
  top: calc(100% + 4px);
  padding: 0.5rem 0.5rem;
  display: none;
  position: absolute;
  z-index: 10;
  border-radius: 0.75rem;
  border-width: 1px;
  width: 100%;
  color: #111827;
  background-color: #ffffff;
  box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
}

.dark #categories-dropdown {
  background-color: rgb(var(--background-dark));
  border-color: #d1d5db1a;
  color: #ffffff;
}

#categories-dropdown-clickout {
  position: fixed;
  top: 0;
  right: 0;
  bottom: 0;
  left: 0;
  z-index: 0;
}

.dropdown-icon-container {
  display: flex;
  position: absolute;
  top: 0;
  bottom: 0;
  right: 0;
  align-items: center;
  padding-right: 0.25rem;
}

.dropdown-icon {
  margin-left: 0.25rem;
  margin-right: 0.75rem;
  flex: none;
  width: 0.75rem;
  height: 0.75rem;
  background-color: #6b7280;
  mask-image: url(https://mintlify.b-cdn.net/v6.5.1/solid/caret-down.svg);
  mask-repeat: no-repeat;
  mask-position: center center;
}

.dark .dropdown-icon {
  background-color: #ffffff80;
}

#prompts-container {
  grid-template-columns: repeat(1, minmax(0, 1fr));
  gap: 2rem;
}

.dropdown-item {
  padding: 0.25rem 0.5rem;
  border-radius: 0.375rem;
  display: flex;
  align-items: center;
  cursor: pointer;
}

.dropdown-item:hover {
  background-color: #f9fafb;
}

.dark .dropdown-item:hover {
  background-color: #ffffff0d;
}

.check-icon {
  mask-image: url(https://mintlify.b-cdn.net/v6.5.1/solid/check.svg);
  height: 0.875rem;
  width: 1rem;
  background-color: rgb(var(--primary-light));
  mask-repeat: no-repeat;
  mask-position: center center;
}

.prompt-card {
  margin: -0.75rem;
  padding: 0.75rem;
  display: flex;
  border-radius: 1rem;
}

.prompt-card:hover {
  background-color: #03071208;
}

.dark .prompt-card:hover {
  background-color: #ffffff08;
}

.prompt-icon-container {
  display: flex;
  flex: none;
  align-items: center;
  justify-content: center;
  margin-right: 1.5rem;
  border-radius: 0.75rem;
  height: 4rem;
  width: 4rem;
  background-color: #cb785c1a;
}

.prompt-icon {
  height: 1.5rem;
  width: 1.5rem;
  background-color: rgb(var(--primary-light));
  mask-repeat: no-repeat;
  mask-position: center center;
}

.prompt-title {
  color: rgb(31 41 55);
  font-weight: 600;
}

.dark .prompt-title {
  color: rgb(229 231 235);
}

.prompt-description {
  margin-top: 0.25rem;
}

#prompts-container {
  display: grid;
  margin-top: 2.5rem;
}

@media (min-width: 640px) {
  #category-select {
    width: 16rem;
  }
}

@media (min-width: 1024px) {
  #prompts-container {
    grid-template-columns: repeat(2, minmax(0, 1fr));
  }
}

/* Utility classes */
.relative {
  position: relative;
}

.flex-1 {
  flex: 1 1 0%;
}


.prompts-container {
  grid-template-columns: repeat(1, minmax(0, 1fr));
  gap: 2rem;
}

@media (min-width: 1024px) {
  .prompts-container {
    grid-template-columns: repeat(2, minmax(0, 1fr));
  }
}


"use client";

function initInkeep() {
  // Get the Mintlify search containers, going to reuse them as the triggers for Inkeep
  const searchButtonContainerIds = [
    "search-bar-entry",
    "search-bar-entry-mobile",
    "home-search-entry",
  ];

  // Clone and replace, needed to remove existing event listeners
  const clonedSearchButtonContainers = searchButtonContainerIds.map((id) => {
    const originalElement = document.getElementById(id);
    if (!originalElement) return null;
    const clonedElement = originalElement.cloneNode(true);
    originalElement.parentNode.replaceChild(clonedElement, originalElement);
    return clonedElement;
  }).filter(Boolean);

  // Customization settings
  const sharedConfig = {
    stylesheetUrls: [
      "https://storage.googleapis.com/customer-imgs/anthropic.css",
    ],
    baseSettings: {
      apiKey: "ee5b7c15ed3553cd6abc407340aad09ac7cb3b9f76d8613a",
      integrationId: "clwtqz9sq001izszu8ms5g4om",
      organizationId: "org_JfjtEvzbwOikUEUn",
      primaryBrandColor: "#181818",
      theme: {
        tokens: {
          fonts: {
            heading: "'Styrene'",
            body: "'Tiempos'",
          },
          colors: {
            'gray.50': '#f9f9f8',
            'gray.100': '#f1f1f0',
            'gray.200': '#e9e8e7',
            'gray.300': '#e2e1df',
            'gray.400': '#cfcec6',
            'gray.500': '#bcb8a9',
            'gray.600': '#8d8c87',
            'gray.700': '#828079',
            'gray.800': '#42413B',
            'gray.900': '#21201C',
          },
        },
      },
      customIcons: {
        search: { builtIn: 'IoSearch' },
      }
    },
    aiChatSettings: {
      chatSubjectName: "Claude",
      botAvatarSrcUrl:
        "https://storage.googleapis.com/organization-image-assets/anthropic-botAvatarSrcUrl-1715877069137.svg",
      botAvatarDarkSrcUrl:
        "https://storage.googleapis.com/organization-image-assets/anthropic-botAvatarDarkSrcUrl-1715877068491.svg",
      getHelpCallToActions: [
        {
          name: "Support Center",
          url: "https://support.anthropic.com/en/",
          icon: {
            builtIn: "IoHelpBuoyOutline",
          },
        },
        {
          name: "Github",
          url: "https://github.com/anthropics",
          icon: {
            builtIn: "FaGithub",
          },
        },
      ],
      quickQuestions: [
        "How do I create structured JSON output?",
        "For few shot prompting, how do I pick examples?",
        "How can I prompt Claude to reply a user's language?",
      ],
    },
  };

  // for syncing with dark mode
  const colorModeSettings = {
    observedElement: document.documentElement,
    isDarkModeCallback: (el) => {
      return el.classList.contains("dark");
    },
    colorModeAttribute: "class",
  };

  // add the "Ask AI" pill chat button
  window.Inkeep().embed({
    componentType: "ChatButton",
    colorModeSync: colorModeSettings,
    properties: sharedConfig,
  });

  // instantiate Inkeep "custom trigger" component (using the Mintlify search bar as the trigger)
  const inkeepSearchModal = window.Inkeep({
    ...sharedConfig.baseSettings,
  }).embed({
    componentType: "CustomTrigger",
    colorModeSync: colorModeSettings,
    properties: {
      ...sharedConfig,
      isOpen: false,
      onClose: () => {
        inkeepSearchModal.render({
          isOpen: false,
        });
      },
      modalSettings: {
        onShortcutKeyPressed: () => {
          inkeepSearchModal.render({
            isOpen: true,
          });
        },
        shortcutKey: "k",
      },
    },
  });

  // Instantiate a separate Inkeep component for the home search entry
  const homeSearchModal = window.Inkeep({
    ...sharedConfig.baseSettings,
  }).embed({
    componentType: "CustomTrigger",
    colorModeSync: colorModeSettings,
    properties: {
      ...sharedConfig,
      isOpen: false,
      onClose: () => {
        homeSearchModal.render({
          isOpen: false,
        });
      },
      modalSettings: {
        defaultView: 'AI_CHAT',
      },
    },
  });

  // When the Mintlify search bar clone is clicked, open the appropriate Inkeep search modal
  clonedSearchButtonContainers.forEach((trigger) => {
    trigger.addEventListener("click", function () {
      if (trigger.id === "home-search-entry") {
        homeSearchModal.render({
          isOpen: true,
        });
      } else {
        inkeepSearchModal.render({
          isOpen: true,
        });
      }
    });
  });
}

// Load the Inkeep script
const inkeepScript = document.createElement("script");
inkeepScript.type = "module";
inkeepScript.src =
  "https://unpkg.com/@inkeep/widgets-embed@0.2.289/dist/embed.js";
document.body.appendChild(inkeepScript);

// Wait for the Inkeep script to load
function waitForInkeep(callback) {
  if (window.Inkeep) {
    callback();
  } else {
    setTimeout(function () {
      waitForInkeep(callback);
    }, 100);
  }
}

// Function to handle URL changes
function handleURLChange() {
  initInkeep();
}

// Once the Inkeep script has loaded, instantiate the Inkeep chat components
waitForInkeep(function () {
  initInkeep();

  // Listen for URL changes using the 'popstate' event
  window.addEventListener("popstate", handleURLChange);

  // Listen for URL changes using the 'hashchange' event (if using hash-based routing)
  window.addEventListener("hashchange", handleURLChange);
});

예시 출력

API 요청

Developer Console

Developer Discord

Support

Console Développeur

Discord pour les développeurs

Assistance

Entwicklerkonsole

Entwickler-Discord

Unterstützung

Console per sviluppatori

Discord per Sviluppatori

Supporto

開発者コンソール

開発者向けDiscord

サポート

Consola de Desarrollador

Discord para Desarrolladores

Soporte

개발자 콘솔

개발자 Discord

지원

开发者控制台

开发者 Discord

支持

開發者控制台

開發者 Discord

支援

Консоль разработчика

Дискорд для разработчиков

Поддержка

Konsol Pengembang

Discord Pengembang

Dukungan

Console do Desenvolvedor

Discord para Desenvolvedores

Suporte

Anthropic

User Guides

Welcome

API Reference

Prompt Library

Release Notes

Developer Newsletter

Guides d'utilisation

Référence de l'API

Bibliothèque de prompts

Benutzerhandbücher

API-Referenz

Prompt-Bibliothek

Guide per l'utente

Riferimento API

Libreria di Prompt

ユーザーガイド

API リファレンス

プロンプトライブラリ

Guías de Usuario

Referencia de la API

Biblioteca de Prompts

사용자 가이드

API 참조

프롬프트 라이브러리

用户指南

API 参考

提示库

使用者指南

API 參考文件

提示語料庫

Руководства пользователя

Справочник по API

Библиотека запросов

Panduan Pengguna

Referensi API

Pustaka Prompt

Guias do Usuário

Referência da API

Go to claude.ai

Research

News

사용자가 제시한 주제에 대해 소크라테스식 대화를 나눕니다.

소크라테스식 현자

Claude is a highly performant, trustworthy, and intelligent AI platform built by Anthropic. Claude excels at tasks involving language, reasoning, analysis, coding, and more.

Overview

Welcome to Claude

Let’s learn how to use the Anthropic API to build with Claude.

Initial setup

Claude is a family of [highly performant and intelligent AI models](/en/docs/about-claude/models) built by Anthropic. While Claude is powerful and extensible, it’s also the most trustworthy and reliable AI available. It follows critical protocols, makes fewer mistakes, and is resistant to jailbreaks—allowing [enterprise customers](https://www.anthropic.com/customers) to build the safest AI-powered applications at scale.

Intro to Claude

Guides to common use cases

This guide walks through how to harness Claude's advanced natural language understanding capabilities to classify customer support tickets at scale based on customer intent, urgency, prioritization, customer profile, and more.

Ticket routing

This guide walks through how to leverage Claude's advanced conversational capabilities to handle customer inquiries in real time, providing 24/7 support, reducing wait times, and managing high support volumes with accurate responses and positive interactions.

Customer support agent

Content moderation is a critical aspect of maintaining a safe, respectful, and productive environment in digital applications. In this guide, we'll discuss how Claude can be used to moderate content within your digital application.

Content moderation

This guide walks through how to leverage Claude's advanced natural language processing capabilities to efficiently summarize legal documents, extracting key information and expediting legal research. With Claude, you can streamline the review of contracts, litigation prep, and regulatory work, saving time and ensuring accuracy in your legal processes.

Legal summarization

Claude is a family of state-of-the-art large language models developed by Anthropic. This guide introduces our models and compares their performance with legacy models. 

Models

Security and compliance

Define success criteria

Define your success criteria

Develop test cases

Create strong empirical evaluations

Prompt engineering overview

Prompt generator

Automatically generate first draft prompt templates

Be clear and direct

Be clear, direct, and detailed

Use examples (multishot prompting)

Use examples (multishot prompting) to guide Claude's behavior

Let Claude think (CoT)

Let Claude think (chain of thought prompting) to increase performance

Use XML tags

Use XML tags to structure your prompts

Give Claude a role (system prompts)

Giving Claude a role with a system prompt

Prefill Claude's response

Prefill Claude's response for greater output control

Chain complex prompts

Chain complex prompts for stronger performance

Long context tips

Long context prompting tips

Claude excels in a wide range of text-based tasks. Claude has been trained to ingest code, prose, and other natural language inputs, and provide text outputs in response.

Text generation

Text embeddings are numerical representations of text that enable measuring semantic similarity. This guide introduces embeddings, their applications, and how to use embedding models for tasks like search, recommendations, and anomaly detection.

Embeddings

The [Claude for Sheets extension](https://workspace.google.com/marketplace/app/claude%5Ffor%5Fsheets/909417792257) integrates Claude into Google Sheets, allowing you to execute interactions with Claude directly in cells.

Google Sheets add-on

The Claude 3 family of models comes with new vision capabilities that allow Claude to understand and analyze images, opening up exciting possibilities for multimodal interaction.

Vision

Tool use (function calling)

Prompt Caching (beta)

Message Batches (beta)

Reduce hallucinations

Increase output consistency

Increase output consistency (JSON mode)

Mitigate jailbreaks

Mitigate jailbreaks and prompt injections

Reduce prompt leak

Keep Claude in character

Keep Claude in character with role prompting and prefilling

Reducing latency

The [Anthropic Console](https://console.anthropic.com/dashboard) features an **Evaluation tool** that allows you to test your prompts under various scenarios.

Using the Evaluation Tool

These concepts are not unique to Anthropic’s language models, but we present a brief summary of key terms below.

Glossary

Model Deprecations

System status

Claude 3 model card

Anthropic Cookbook

Anthropic Courses

Anthropic Privacy Policy

Getting started

Anthropic services live at a fixed range of IP addresses. You can add these to your firewall to open the minimum amount of surface area for egress traffic when accessing the Anthropic API and Console. These ranges will not change without notice.

IP addresses

When making API requests, you must send an `anthropic-version` request header. For example, `anthropic-version: 2023-06-01`. If you are using our [client libraries](/en/api/client-libraries), this is handled for you automatically.

Versions

Errors

To mitigate against misuse and manage capacity on our API, we have implemented limits on how much an organization can use the Claude API.

Rate limits

We provide libraries in Python and Typescript that make it easier to work with the Anthropic API.

Client SDKs

Here are the countries, regions, and territories we can currently support access from:

Supported regions

We've tried to provide the answers to the most common questions in these docs. However, if you need further technical support using Claude, the Anthropic API, or any of our products, you may reach our support team at [support.anthropic.com](https://support.anthropic.com).

Getting help

Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation.

The Messages API can be used for either single queries or stateless multi-turn conversations.

Create a Message

Streaming Messages

Migrating from Text Completions to Messages

Migrating from Text Completions

Request and response examples for the Messages API

Messages examples

Send a batch of Message creation requests.

The Message Batches API can be used to process multiple Messages API requests at once. Once a Message Batch is created, it begins processing immediately. Batches can take up to 24 hours to complete.

Create a Message Batch (beta)

This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the `results_url` field in the response.

Retrieve a Message Batch (beta)

Streams the results of a Message Batch as a `.jsonl` file.

Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests.

Retrieve Message Batch Results (beta)

List all Message Batches within a Workspace. Most recently created batches are returned first.

List Message Batches (beta)

Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation.

The number of canceled requests is specified in `request_counts`. To determine which requests were canceled, check the individual results within the batch. Note that cancellation may not result in any canceled requests if they were non-interruptible.

Cancel a Message Batch (beta)

Example usage for the Message Batches API

Message Batches examples

[Legacy] Create a Text Completion.

The Text Completions API is a legacy API. We recommend using the [Messages API](https://docs.anthropic.com/en/api/messages) going forward.

Future models and features will not be compatible with Text Completions. See our [migration guide](https://docs.anthropic.com/en/api/migrating-from-text-completions-to-messages) for guidance in migrating from Text Completions to Messages.

Create a Text Completion

Streaming Text Completions

Prompt validation

Anthropic’s Claude models are now generally available through Amazon Bedrock.

Amazon Bedrock API

Anthropic’s Claude models are now generally available through [Vertex AI](https://cloud.google.com/vertex-ai).

Vertex AI API

Library

Generate an interactive speed typing game in a single HTML file, featuring side-scrolling gameplay and Tailwind CSS styling.

Cosmic Keystrokes

프롬프트 라이브러리

​예시 출력

​API 요청

예시 출력

API 요청