Anthropic’s Claude Sonnet 4 AI model now supports a massive context window of up to 1 million tokens on the Anthropic API, a significant increase that is five times larger than its previous capacity. This enhancement enables developers and businesses to process extremely large datasets in a single request, opening new possibilities for AI in software development, document analysis, and multi-step workflows.

Breaking the Limits: What 1 Million Tokens Means

The upgrade to a 1 million token context window allows Claude Sonnet 4 to handle extensive contents such as complete codebases comprising over 75,000 lines of code or the equivalent of dozens of research papers at once. For comparison, 1 million tokens is roughly equal to the entire set of Harry Potter books, enabling AI interactions at an unprecedented scale in a single prompt.

New Use Cases Unlocked by Longer Context

With this expanded context, Claude Sonnet 4 can support a variety of complex, large-scale applications:

• Large-scale Code Analysis: Developers can feed entire software projects, including source files, tests, and documentation, into the model. Claude can then analyze project architecture, discover cross-file dependencies, and recommend improvements considering the entire system design.
• Document Synthesis: Enterprises dealing with vast collections of documents, such as legal contracts, scientific research papers, or technical manuals, can use Claude to synthesize information across hundreds of documents without losing context.
• Context-aware AI Agents: This ability helps create agents that maintain state over extensive tool calls and intricate workflows by incorporating API documentation, tool specifications, and interaction histories in one coherent model session.

Adjusted Pricing for Higher Context Usage

Due to increased computational demands, Anthropic has updated its pricing for prompts exceeding 200,000 tokens.

Highlights from Industry Leaders

Claude Sonnet 4 remains our go-to model for code generation workflows, consistently outperforming other leading models in production. With the 1M context window, developers can now work on significantly larger projects while maintaining the high accuracy we need for real-world coding.

Eric Simons, CEO and Co-founder of Bolt.new.

What was once impossible is now reality: Claude Sonnet 4 with 1M token context has supercharged autonomous capabilities in Maestro, our software engineering agent at iGent AI. This leap unlocks true production-scale engineering—multi-day sessions on real-world codebases—establishing a new paradigm in agentic software engineering.

Sean Ward, CEO and Co-founder of iGent AI.

Why This Matters

Longer context windows enable AI models like Claude Sonnet 4 to truly grasp and work with comprehensive datasets without losing track of earlier information, which is critical for tasks that need deep understanding over extended input. This advancement marks a breakthrough for those looking to harness AI for complex problem-solving, coding, and document management at scale.

How to Get Started

Interested developers and organizations can access Claude Sonnet 4’s 1 million token context support now through Anthropic’s public beta API with expanded availability on Amazon Bedrock and soon on Google Cloud’s Vertex AI. Detailed documentation and pricing information are available on Anthropic’s official website to help users maximize this powerful context capability.

This development positions Claude Sonnet 4 as a leading choice for enterprises and developers who need AI that can handle large volumes of data and complex workflows with precision and reliability.