Claude Sonnet 5.5

Anthropic’s balanced middle tier for everyday coding and agent work, using fewer tokens per task than Sonnet 5. It has a 1M tokens context window. Through Anthropic’s API it costs $2.00 per million input tokens and $10.00 per million output tokens.

Among the tools we track, it’s available in Claude Code, Copilot, Cursor, Kiro, Zed and Amp. Claude Code needs version 2.1.284 or later. It’s also the default model for Cline’s own provider.

What Anthropic reports

• Anthropic reports 70.6% on Terminal-Bench 4.0
• Anthropic reports 55.5% on CursorBench 4.0

Vendor-reported figures, not independently verified by Code×Radar.

Related changes

• Cline 4.1.26 changes default models and adds a model setting for cloud tasks · October 26, 2026
• Cline 4.1.25 starts rolling out cloud sessions · October 16, 2026
• Claude Sonnet 4 reaches end of life in Kiro · October 14, 2026
• Claude Sonnet 5.5 becomes Claude Code's default Sonnet model · September 28, 2026

Sources

• platform.claude.com: overview
• platform.claude.com: pricing
• anthropic.com: claude sonnet 5 5
• docs.github.com: supported models
• cursor.com: models

Facts last checked November 15, 2026.