Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)

Claude Sonnet 5.5 is Anthropic’s September 2026 model for everyday agentic coding, document creation, and knowledge work. It supports text and image input, text output, a 1M-token context window, and 128K output tokens. Adaptive thinking defaults to high effort on the API and medium in Claude Code and Claude apps; between_tools turns off up-front thinking at high effort or below. Reliable knowledge and training-data cutoffs are June 2026. Standard prices per million tokens are $2 input, $10 output, $0.20 cache reads, $2.50 for 5-minute cache writes, and $4 for 1-hour cache writes. Higher-risk cybersecurity requests can fall back to Sonnet 5. Launch benchmarks include evaluation-specific effort levels and pre-release deployment caveats.