Claude Sonnet 4 vs Claude Sonnet 4.6 Thinking
Both have similar output pricing, while Claude Sonnet 4.6 Thinking offers a larger context window. Choose Claude Sonnet 4 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 | Claude Sonnet 4.6 Thinking |
|---|---|---|
| Provider | Anthropic | NanoGPT |
| Input / 1M tokens | $3.00 | $3.00 |
| Output / 1M tokens | $15.00 | $15.00 |
| Context window | 200K | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | May 2025 | Feb 2026 |
| SWE-bench Verified score | 76.8 | — |
| Aider Polyglot score | 61.3 | — |
| LMArena (Chatbot Arena) Elo score | 1351 | — |
| LMArena Vision Elo score | 1191 | — |
| GPQA Diamond score | 78.3 | — |
| FrontierMath score | 4.1 | — |
| Epoch Capabilities Index score | 142 | — |
| LiveBench score | — | 75.7 |
FAQ
Is Claude Sonnet 4 or Claude Sonnet 4.6 Thinking cheaper?
Claude Sonnet 4 and Claude Sonnet 4.6 Thinking have comparable output pricing.
Which has the larger context window, Claude Sonnet 4 or Claude Sonnet 4.6 Thinking?
Claude Sonnet 4.6 Thinking has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.