Claude Sonnet 4 vs Claude 3.5 Sonnet
Both have similar output pricing. Choose Claude Sonnet 4 or Claude 3.5 Sonnet based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude Sonnet 4 | Claude 3.5 Sonnet |
|---|---|---|
| Provider | Anthropic | DigitalOcean |
| Input / 1M tokens | $3.00 | $3.00 |
| Output / 1M tokens | $15.00 | $15.00 |
| Context window | 200K | 200K |
| Parameters | — | — |
| Open weights | No | No |
| Released | May 2025 | Jun 2024 |
| SWE-bench Verified score | 76.8 | 63.4 |
| Aider Polyglot score | 61.3 | 51.6 |
| LMArena (Chatbot Arena) Elo score | 1351 | 1298 |
| LMArena Vision Elo score | 1191 | 1125 |
| GPQA Diamond score | 78.3 | 55.3 |
| FrontierMath score | 4.1 | 2.1 |
| Epoch Capabilities Index score | 142 | 134 |
| SWE-bench Multimodal score | — | 25.3 |
FAQ
Is Claude Sonnet 4 or Claude 3.5 Sonnet cheaper?
Claude Sonnet 4 and Claude 3.5 Sonnet have comparable output pricing.
Which has the larger context window, Claude Sonnet 4 or Claude 3.5 Sonnet?
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.