Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Claude 4.1 Opus (Non-reasoning) | o1-preview |
|---|---|---|
| Input ($/M tokens) | $15 | $16.5 |
| Output ($/M tokens) | $75 | $66 |
Data from Artificial Analysis API — 12 benchmarks
o1-preview is cheaper overall. Its blended price (3:1 input/output ratio) is $28.88/M tokens vs $30.00/M for Claude 4.1 Opus (Non-reasoning).
o1-preview wins 2 out of 12 benchmarks compared to 1 for Claude 4.1 Opus (Non-reasoning). See the detailed benchmark chart above for per-category results.
Claude 4.1 Opus (Non-reasoning) generates tokens faster at 35 tok/s vs 0 tok/s. However, o1-preview has lower time-to-first-token (0.00s vs 1.34s).
Choose based on your priorities: o1-preview for lower cost, o1-preview for stronger benchmark performance, and Claude 4.1 Opus (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.