We recommend using Claude Sonnet 5. It’s the latest Sonnet with stronger capabilities at a lower price.
Sonnet 4.6 is Anthropic’s medium-tier intelligence model. It costs the same as Sonnet 4.5 and supports thinking mode with context windows up to 1M tokens. It’s a solid pick for teams standardized on Claude who want reasoning without Opus pricing.
Strengths¶
- More affordable than Opus while keeping strong coding abilities and thinking support. Good for everyday coding tasks.
- Supports extended reasoning for tasks that benefit from deeper analysis.
- Same provider and style as Opus at a lower price point.
Limitations¶
- Codex and Composer offer more capability per dollar for most coding tasks.
- For peak quality, Opus remains the stronger choice.
Tools¶
Sonnet 4.6 has access to all agent tools when used with Cursor including:
Learn more about how tools work and tool calling fundamentals.
Pricing¶
Cursor plans include two usage pools. Sonnet 4.6 draws from the third-party Other Models pool, which charges at the rates below. All prices are per million tokens.
All Sonnet 4.6 prompts bill at the base per-token rates in the table above, including when context goes above 200k. There is no separate long-context multiplier for Sonnet 4.6.
A thinking variant is available for deeper reasoning.