| 1M token context window | An extended context window that allows you to process much larger documents, maintain longer conversations, and work with more extensive codebases. | |
| 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. | |
| Batch processing | Process large volumes of requests asynchronously for cost savings. Send batches with a large number of queries per batch. Batch API calls costs 50% less than standard API calls. | |
| 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. | |
| 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. | |
| Extended thinking | Enhanced reasoning capabilities for complex tasks, providing transparency into Claude’s step-by-step thought process before delivering its final answer. | |
| Files API | Upload and manage files to use with Claude without re-uploading content with each request. Supports PDFs, images, and text files. | |
| PDF support | Process and analyze text and visual content from PDF documents. | |
| Prompt caching (5m) | Provide Claude with more background knowledge and example outputs to reduce costs and latency. | |
| Prompt caching (1hr) | Extended 1-hour cache duration for less frequently accessed but important context, complementing the standard 5-minute cache. | |
| 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. | |
| Structured outputs | Guarantee schema conformance with two approaches: JSON outputs for structured data responses, and strict tool use for validated tool inputs. Available on Sonnet 4.5 and Opus 4.1. | |
| 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. | |
| Tool use | Enable Claude to interact with external tools and APIs to perform a wider variety of tasks. For a list of supported tools, see the Tools table. | |
