Batch processing

Process large volumes of requests asynchronously for cost savings. Send batches with a large number of queries per batch. Each batch is processed in less than 24 hours and costs 50% less than standard API calls. Learn more.

Available on:

  • Anthropic API
  • Amazon Bedrock
  • Google Cloud’s Vertex AI

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. Learn more.

Available on:

  • Anthropic API
  • Google Cloud’s Vertex AI

Computer use (public beta)

Computer use is Claude’s ability to perform tasks by interpreting screenshots and automatically generating the necessary computer commands (like mouse movements and keystrokes). Learn more.

Available on:

  • Anthropic API
  • Amazon Bedrock
  • Google Cloud’s Vertex AI

PDF support

Process and analyze text and visual content from PDF documents. Learn more.

Available on:

  • Anthropic API
  • Google Cloud’s Vertex AI

Prompt caching

Provide Claude with more background knowledge and example outputs to reduce costs by up to 90% and latency by up to 85% for long prompts. Learn more.

Available on:

  • Anthropic API
  • Amazon Bedrock
  • Google Cloud’s Vertex AI

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. Learn more.

Available on:

  • Anthropic API
  • Google Cloud’s Vertex AI

Tool use

Enable Claude to interact with external tools and APIs to perform a wider variety of tasks. Learn more.

Available on:

  • Anthropic API
  • Amazon Bedrock
  • Google Cloud’s Vertex AI