Tổng quan tính năng nền tảng Claude API
Trust: ★★★☆☆ (0.90) · 0 validations · factual
Published: 2026-05-09 · Source: crawler_authoritative
Tình huống
Tài liệu hướng dẫn kỹ thuật về các tính năng và khả năng của nền tảng Claude API, bao gồm Model capabilities, Tools, Tool infrastructure, Context management và Files and assets.
Insight
Nền tảng Claude API được tổ chức thành 5 lĩnh vực chính: (1) Model capabilities - kiểm soát cách Claude suy luận và định dạng phản hồi, bao gồm Context windows lên đến 1M tokens, Adaptive thinking cho phép Claude quyết định động thời gian suy nghĩ, Extended thinking cho reasoning nâng cao, Effort parameter để điều chỉnh độ chi tiết phản hồi, PDF support, Search results cho RAG, Structured outputs đảm bảo tuân thủ schema, và Batch processing giảm 50% chi phí; (2) Tools - bao gồm server-side tools (Advisor tool, Code execution, Web fetch, Web search) và client-side tools (Bash, Computer use, Memory, Text editor); (3) Tool infrastructure - Agent Skills, MCP connector, Tool search, Fine-grained tool streaming, Programmatic tool calling; (4) Context management - Compaction tự động tóm tắt context, Context editing, Automatic prompt caching, Prompt caching 5 phút và 1 giờ, Token counting; (5) Files and assets - Files API để upload và quản lý file. Trạng thái availability: Beta (preview), Generally available (GA - production-ready), Deprecated, Retired. Zero Data Retention (ZDR) eligible cho nhiều tính năng. Batch API calls có chi phí thấp hơn 50% so với standard API calls.
Hành động
- Sử dụng Models API (/docs/en/api/models/list) để khám phá programmatic các khả năng của model; - Với người mới bắt đầu: ưu tiên học Model capabilities và Tools trước; - Khi cần optimize cost, latency, hoặc scale: quay lại các phần khác; - Sử dụng beta header cho các beta features; - Tham khảo Admin API, Usage and Cost API, Compliance API cho administration và governance; - Code execution được miễn phí khi sử dụng với web search hoặc web fetch; - Cấu hình data residency bằng inference_geo parameter (global hoặc us).
Điều kiện áp dụng
Nội dung dành cho developers và data scientists xây dựng ứng dụng với Claude API. Batch processing hiện chỉ available trên claudeApi, bedrock, vertexAi. Computer use tool chỉ available trên beta versions. Data residency chỉ available trên claudeApi platform.
Nội dung gốc (Original)
Features overview
Explore Claude’s advanced features and capabilities.
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 table below). 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 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. |
* May carry a qualifier indicating narrower availability or added constraints (for example, “beta: research preview”). See the feature’s page for details.
Model capabilities
Ways to steer Claude and Claude’s direct outputs, including response format, reasoning depth, and input modalities.
| Feature | Description | Zero Data Retention (ZDR) | Availability |
|---|---|---|---|
| Context windows | Up to 1M tokens for processing large documents, extensive codebases, and long conversations. | ZDR eligible | |
| Adaptive thinking | Let Claude dynamically decide when and how much to think. The recommended thinking mode for Opus 4.7. Use the effort parameter to control thinking depth. | ZDR eligible | |
| 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 | |
| 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 | |
| Data residency | Control where model inference runs using geographic controls. Specify "global" or "us" routing per request via the inference_geo parameter. | ZDR eligible | |
| Effort | Control how many tokens Claude uses when responding with the effort parameter, trading off between response thoroughness and token efficiency. Supported on Opus 4.7, Opus 4.6, and Opus 4.5. | ZDR eligible | |
| Extended thinking | Enhanced reasoning capabilities for complex tasks, providing transparency into Claude’s step-by-step thought process before delivering its final answer. | ZDR eligible | |
| PDF support | Process and analyze text and visual content from PDF documents. | ZDR eligible | |
| Search results | Enable natural citations for RAG applications by providing search results with proper source attribution. Achieve web search-quality citations for custom knowledge bases and tools. | ZDR eligible | |
| Structured outputs | Guarantee schema conformance with two approaches: JSON outputs for structured data responses, and strict tool use for validated tool inputs. | ZDR eligible (qualified)* |
Tools
Built-in tools that Claude invokes via tool_use. Server-side tools are run by the platform; client-side tools are implemented and executed by you.
Server-side tools
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Advisor tool | Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation for long-horizon agentic workloads. | ZDR eligible | |
| Code execution | Run code in a sandboxed environment for advanced data analysis, calculations, and file processing. Free when used with web search or web fetch. | Not ZDR eligible | |
| Web fetch | Retrieve full content from specified web pages and PDF documents for in-depth analysis. | ZDR eligible* | |
| Web search | Augment Claude’s comprehensive knowledge with current, real-world data from across the web. | ZDR eligible* |
Client-side tools
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Bash | Execute bash commands and scripts to interact with the system shell and perform command-line operations. | ZDR eligible | |
| Computer use | Control computer interfaces by taking screenshots and issuing mouse and keyboard commands. | ZDR eligible | |
| Memory | Enable Claude to store and retrieve information across conversations. Build knowledge bases over time, maintain project context, and learn from past interactions. | ZDR eligible | |
| Text editor | Create and edit text files with a built-in text editor interface for file manipulation tasks. | ZDR eligible |
Tool infrastructure
Infrastructure that supports discovering, orchestrating, and scaling tool use.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Agent Skills | Extend Claude’s capabilities with Skills. Use pre-built Skills (PowerPoint, Excel, Word, PDF) or create custom Skills with instructions and scripts. Skills use progressive disclosure to efficiently manage context. | Not ZDR eligible | |
| Fine-grained tool streaming | Stream tool use parameters without buffering/JSON validation, reducing latency for receiving large parameters. | ZDR eligible | |
| MCP connector | Connect to remote MCP servers directly from the Messages API without a separate MCP client. | Not ZDR eligible | |
| Programmatic tool calling | Enable Claude to call your tools programmatically from within code execution containers, reducing latency and token consumption for multi-tool workflows. | Not ZDR eligible | |
| Tool search | Scale to thousands of tools by dynamically discovering and loading tools on-demand using regex-based search, optimizing context usage and improving tool selection accuracy. | ZDR eligible |
Context management
Infrastructure for controlling and optimizing Claude’s context window.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Compaction | Server-side context summarization for long-running conversations. When context approaches the window limit, the API automatically summarizes earlier parts of the conversation. Supported on Opus 4.7, Opus 4.6, and Sonnet 4.6. | ZDR eligible | |
| Context editing | Automatically manage conversation context with configurable strategies. Supports clearing tool results when approaching token limits and managing thinking blocks in extended thinking conversations. | ZDR eligible | |
| Automatic prompt caching | Simplify prompt caching to a single API parameter. The system automatically caches the last cacheable block in your request, moving the cache point forward as conversations grow. | ZDR eligible | |
| Prompt caching (5m) | Provide Claude with more background knowledge and example outputs to reduce costs and latency. | ZDR eligible | |
| Prompt caching (1hr) | Extended 1-hour cache duration for less frequently accessed but important context, complementing the standard 5-minute cache. | ZDR eligible | |
| Token counting | Token counting enables you to determine the number of tokens in a message before sending it to Claude, helping you make informed decisions about your prompts and usage. | ZDR eligible |
Files and assets
Manage files and assets for use with Claude.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Files API | Upload and manage files to use with Claude without re-uploading content with each request. Supports PDFs, images, and text files. | Not ZDR eligible |
* Structured outputs: Your prompts and Claude’s outputs are not stored. Only JSON schemas are cached, for up to 24 hours since last use. Web search and web fetch: ZDR-eligible except when dynamic filtering is enabled. See ZDR details.
Liên kết
- Nền tảng: Claude Api · Bedrock · Vertex Ai · Azure Ai
- Nguồn: https://platform.claude.com/docs/en/build-with-claude/overview.md
Xem thêm: