Anthropic has announced that Claude Sonnet 4 now supports an impressive 1 million token context window on its API, a 5x increase that enables developers to process vast datasets, such as entire codebases exceeding 75,000 lines or extensive collections of research papers, in a single request. This feature is now in public beta on the Anthropic API and Amazon Bedrock, with support for Google Cloud’s Vertex AI expected soon.

Expanded Use Cases with Long Context

The expanded context window unlocks powerful possibilities for developers, including:

1. Large-Scale Code Analysis: Developers can load complete codebases, including source files, tests, and documentation. Claude can analyze project architecture, trace cross-file dependencies, and provide system-wide improvement suggestions.
2. Document Synthesis: Process large document sets, such as legal contracts, technical specifications, or research papers, while maintaining full context across hundreds of documents.
3. Context-Aware Agents: Build AI agents that retain coherence across complex, multi-step workflows, incorporating extensive API documentation, tool definitions, and interaction histories.

Getting Started

Long context support is currently available in public beta for Anthropic API customers with Tier 4 and custom rate limits, with broader rollout planned in the coming weeks. It is also accessible via Amazon Bedrock and will soon be available on Google Cloud’s Vertex AI. For more details, visit Anthropic’s documentation and pricing page.

This breakthrough in context window size positions Claude Sonnet 4 as a game-changer for developers working on complex, data-intensive AI applications.

Source: Anthropic