Compare models
Comparing 2models. Drop the URL into a doc — it's permalinked.
| Field | deepseek/deepseek-chat | anthropic/claude-sonnet-4-5 |
|---|---|---|
| Provider | deepseek | anthropic |
| Model ID | deepseek-chat | claude-sonnet-4-5 |
| Context | 164K | 200K |
| Max output | 8K | 64K |
| Input / 1M | $0.32 | $3.00 |
| Output / 1M | $0.89 | $15.00 |
| Cached input / 1M | $0.07 | $0.30 |
| Avg cost / 1M | $0.60 | $9.00 |
| Speed | 50 t/s | 95 t/s |
| Quality index | 72.0 | 73.0 |
| MMLU | 87.1 | 88.7 |
| GPQA | 59.1 | 71.5 |
| HumanEval | 89.0 | 89.1 |
| MATH | 90.2 | 91.8 |
| SWE-bench | — | 49.0 |
| Arena Elo | — | — |
| Tools | ✓ | ✓ |
| Vision | — | ✓ |
| Thinking | — | ✓ |
| Streaming | ✓ | ✓ |
| JSON mode | ✓ | — |
| Structured output | ✓ | ✓ |
| Prompt cache | — | ✓ |
Same data, in your terminal: relay models compare deepseek-v3 sonnet-4.5