Claude Sonnet 4 now supports up to 1 million tokens of context, a 5x increase that enables processing entire codebases with 75,000+ lines of code or dozens of research papers in a single request. The expanded context window enables large-scale code analysis, document synthesis, and context-aware agents. Pricing increases for prompts over 200K tokens, but costs can be reduced through prompt caching and batch processing. The feature is available in public beta on Anthropic API and Amazon Bedrock, with Google Cloud Vertex AI support coming soon.
Table of contents
Longer context, more use casesAPI pricingCustomer spotlight: Bolt.newCustomer spotlight: iGent AIGet startedSort: