Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | o3-mini (high) | Claude 4.5 Haiku (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $1.1 | $1 |
| Output ($/M tokens) | $4.4 | $5 |
Data from Artificial Analysis API — 12 benchmarks
o3-mini (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.93/M tokens vs $2.00/M for Claude 4.5 Haiku (Non-reasoning).
o3-mini (high) wins 7 out of 12 benchmarks compared to 5 for Claude 4.5 Haiku (Non-reasoning). See the detailed benchmark chart above for per-category results.
o3-mini (high) generates tokens faster at 148 tok/s vs 103 tok/s. However, Claude 4.5 Haiku (Non-reasoning) has lower time-to-first-token (0.47s vs 23.74s).
Choose based on your priorities: o3-mini (high) for lower cost, o3-mini (high) for stronger benchmark performance, and o3-mini (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.