Claude Sonnet 4.5 vs Claude Sonnet 4.6 Thinking
Both have similar output pricing. Choose Claude Sonnet 4.5 or Claude Sonnet 4.6 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude Sonnet 4.5 | Claude Sonnet 4.6 Thinking |
|---|---|---|
| Provider | Anthropic | NanoGPT |
| Input / 1M tokens | $3.00 | $3.00 |
| Output / 1M tokens | $15.00 | $15.00 |
| Context window | 1M | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Sep 2025 | Feb 2026 |
| LiveBench score | 67.9 | 75.7 |
| SWE-bench Verified score | 74.8 | — |
| SWE-bench Multilingual score | 67.0 | — |
| LMArena (Chatbot Arena) Elo score | 1438 | — |
| LMArena WebDev Elo score | 1393 | — |
| GPQA Diamond score | 82.3 | — |
| FrontierMath score | 15.2 | — |
| Epoch Capabilities Index score | 147 | — |
FAQ
Is Claude Sonnet 4.5 or Claude Sonnet 4.6 Thinking cheaper?
Claude Sonnet 4.5 and Claude Sonnet 4.6 Thinking have comparable output pricing.
Which has the larger context window, Claude Sonnet 4.5 or Claude Sonnet 4.6 Thinking?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.