콘텐츠로 이동

Build with Claude#

Claude Platform Docs

API reference

EnglishConsoleLog in



Search

⌘K

First steps

Intro to ClaudeGet your API keyQuickstartAuthentication

Building with Claude

Features overviewUsing the Messages APIStop reasons and fallbackRefusals and fallbackFallback credit

Model capabilities

EffortTask budgets (beta)Fast mode (research preview)Structured outputsCitationsStreaming MessagesBatch processingSearch resultsStreaming refusalsMultilingual supportEmbeddings

Thinking

Tools

OverviewHow tool use worksTutorial: Build a tool-using agentDefine toolsHandle tool callsParallel tool useTool Runner (SDK)Strict tool useServer toolsWeb search toolWeb fetch toolCode execution toolAdvisor toolTool search toolMemory toolBash toolText editor toolComputer use toolTroubleshooting

Tool infrastructure

Tool referenceManage tool contextTool combinationsTool use with prompt cachingProgrammatic tool callingFine-grained tool streaming

Context management

Context windowsCompactionContext editingPrompt cachingMid-conversation system messages and tool changesBuild an orchestration modeCache diagnostics (beta)Token counting

Working with files

Files APIPDF support

Images and vision

Skills

OverviewQuickstartBest practicesSkills for enterpriseSkills in the API

MCP

Remote MCP serversMCP connector

MCP tunnels

Claude on cloud platforms

Amazon Bedrock (Opus 4.7 and later)Amazon Bedrock (Opus 4.6 and earlier)Claude Platform on AWSGoogle CloudMicrosoft Foundry

Log in

MessagesFeatures overview

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Loading

Claude Platform Docs

Solutions#

Partners#

Learn#

Company#

Learn#

Help and security#

Terms and policies#

Messages/Building with Claude

Features overview#

Copy page

Explore Claude's advanced features and capabilities.

Copy page

Claude's API surface is organized into five areas:

  • Model capabilities: Control how Claude reasons and formats responses.
  • Tools: Let Claude take actions on the web or in your environment.
  • Tool infrastructure: Handles discovery and orchestration at scale.
  • Context management: Keeps long-running sessions efficient.
  • Files and assets: Manage the documents and data you provide to Claude.

If you're new, start with model capabilities and tools. Return to the other sections when you're ready to optimize cost, latency, or scale.

For administration and governance, see the Admin API, the Usage and Cost API, and the Compliance API.

#

Feature availability

Features on the Claude Platform are assigned one of the following availability classifications per platform (shown in the Availability column of each following table). Not all features pass through every stage. A feature may enter at any classification and may skip stages.

Classification Description
Beta Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced.

Features may change significantly or be discontinued based on feedback. Not guaranteed for ongoing production use. Breaking changes are possible with notice, and some platform-specific limitations may apply. Beta features on the Claude API and Claude Platform on AWS have a beta header.
Generally available (GA)| Feature is stable, fully supported, and recommended for production use. Should not have a beta header or other indicator that the feature is in a preview state. Covered by standard API versioning guarantees.
Deprecated| Feature is still functional but no longer recommended. A migration path and removal timeline are provided.
Retired| Feature is no longer available.

Platform labels: Claude API (Anthropic first-party) · Bedrock (AWS-operated) · Claude Platform on AWS (Anthropic-operated on AWS) · Google Cloud (Google-operated) · Microsoft Foundry (Anthropic-operated on Azure)

#

Model capabilities

Ways to steer Claude and Claude's direct outputs, including response format, reasoning depth, and input modalities.

You can discover which capabilities a model supports programmatically. The Models API returns max_input_tokens, max_tokens, and a capabilities object for every available model.

The ZDR column indicates whether a feature is available under a Zero Data Retention arrangement. For most features this depends only on what the feature mechanism retains; for features tied to specific models, model-level ZDR availability also applies. See Model-specific data retention requirements.

Feature Description Zero Data Retention (ZDR) Availability
Context windows Up to 1M tokens for processing large documents, extensive code bases, and long conversations. ZDR eligible Claude API (GA)

Bedrock (GA)

Claude Platform on AWS (GA)

Google Cloud (GA)

Microsoft Foundry (GA)
Adaptive thinking| Let Claude dynamically decide when and how much to think. The only thinking mode on Claude 4.7 and later models. Use the effort parameter to control thinking depth.| ZDR eligible| Claude API (GA)

Bedrock (GA)

Claude Platform on AWS (GA)

Google Cloud (GA)

Microsoft Foundry (GA)
Batch processing| Process large volumes of requests asynchronously for cost savings. Send batches with a large number of queries per batch. Batch API calls cost 50% less than standard API calls.| Not ZDR eligible| Claude API (GA)

Claude Platform on AWS (GA)
Citations| Ground Claude's responses in source documents. With Citations, Claude can provide detailed references to the exact sentences and passages it uses to generate responses, leading to more verifiable, trustworthy outputs.| ZDR eligible| Claude API (GA)

Bedrock (GA)

Claude Platform on AWS (GA)

Google Cloud (GA)

Microsoft Foundry (GA)
Data residency| Control where model inference runs using geographic controls. Specify "global" or "us" routing per request through the inference_geo parameter.| ZDR eligible| Claude API (GA)

Claude Platform on AWS (GA)
Effort| Control how many tokens Claude uses when responding with the effort parameter, trading off between response thoroughness and token efficiency.| ZDR eligible| Claude API (GA)

Bedrock (GA)

Claude Platform on AWS (GA)

Google Cloud (GA)

Microsoft Foundry (GA)
Fallback credit| Avoid paying the prompt-cache cost twice when you retry a refused request on another model. The refusal carries a credit token, and echoing it on the retry bills the retry as though the conversation had been on the new model all along. Message Batches results do not include fallback credit tokens.| Not ZDR eligible*| Claude API (Beta)

Bedrock (Beta)

Claude Platform on AWS (Beta)

Google Cloud (Beta)

Microsoft Foundry (Beta)
PDF support| Process and analyze text and vis