Claude Sonnet 5 vs DeepSeek V4 Flash 0731
Claude Sonnet 5 vs DeepSeek V4 Flash 0731: which AI model is cheaper, has the larger context window and more capabilities? Side-by-side comparison updated daily.
Quick verdict
- DeepSeek V4 Flash 0731 is 43× cheaper than Claude Sonnet 5 for the same mix of input and output tokens.
- DeepSeek V4 Flash 0731 has the larger context window (1M), useful for long documents and big codebases.
- DeepSeek V4 Flash 0731 is the more recent release (Jul 31, 2026).
- Only DeepSeek V4 Flash 0731 has openly published weights you can run yourself.
- Only Claude Sonnet 5 accepts images as input.
- Claude Sonnet 5 scores higher on independent tests (overall index 156.3 vs 154.5).
- Choose DeepSeek V4 Flash 0731 if cost matters most; choose Claude Sonnet 5 if you need its specific strengths above. For the best results, test both on your own prompts.
| Claude Sonnet 5 | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Company | Anthropic | DeepSeek |
| Released | Jun 30, 2026 | Jul 31, 2026 ● |
| Overall index | 156.3 ● | 154.5 |
| GPQA Diamond | 90.5% | 91.0% ● |
| AIME math | 94.7% ● | 94.4% |
| FrontierMath | 65.6% ● | 57.5% |
| SimpleQA Verified | 33.7% ● | 33.6% |
| Input (per 1M tokens) | $2 | $0.018 ● |
| Output (per 1M tokens) | $10 | $0.32 ● |
| Cost for 1M input + 1M output tokens | $12.00 | $0.338 ● |
| Providers | 10 | 30 ● |
| Context | 1M | 1M ● |
| Max output | 128K | 944K ● |
| Inputs | Text, Image, Files ● | Text |
| Outputs | Text | Text |
| Reasoning | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Open weights | — | ✓ |