Claude Sonnet 4.6 vs DeepSeek V4 Pro
DeepSeek V4 Pro is cheaper on output tokens. Choose Claude Sonnet 4.6 or DeepSeek V4 Pro based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude Sonnet 4.6 | DeepSeek V4 Pro |
|---|---|---|
| Provider | Anthropic | CrofAI |
| Input / 1M tokens | $3.00 | $0.35 |
| Output / 1M tokens | $15.00 | $0.80 |
| Context window | 1M | 1M |
| Parameters | — | 1.6T |
| Open weights | — | Yes |
| Released | — | Apr 2026 |
| LMArena (Chatbot Arena) Elo score | 1458 | — |
| GPQA Diamond score | 87.4 | — |
| FrontierMath score | 32.4 | — |
| Epoch Capabilities Index score | 153 | — |
| LMArena WebDev Elo score | 1523 | — |
| LMArena Vision Elo score | 1283 | — |
| LiveBench score | — | 74.4 |
FAQ
Is Claude Sonnet 4.6 or DeepSeek V4 Pro cheaper?
DeepSeek V4 Pro is cheaper on output tokens ($0.80 vs $15.00 per 1M).
Which has the larger context window, Claude Sonnet 4.6 or DeepSeek V4 Pro?
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.