Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Claude 3 Haiku | GPT-5.4 nano (xhigh) |
|---|---|---|
| Input ($/M tokens) | $0.25 | $0.2 |
| Output ($/M tokens) | $1.25 | $1.25 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.4 nano (xhigh) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.46/M tokens vs $0.50/M for Claude 3 Haiku.
GPT-5.4 nano (xhigh) wins 7 out of 12 benchmarks compared to 2 for Claude 3 Haiku. See the detailed benchmark chart above for per-category results.
GPT-5.4 nano (xhigh) generates tokens faster at 193 tok/s vs 132 tok/s. Claude 3 Haiku also has lower time-to-first-token (0.41s vs 2.69s).
Choose based on your priorities: GPT-5.4 nano (xhigh) for lower cost, GPT-5.4 nano (xhigh) for stronger benchmark performance, and GPT-5.4 nano (xhigh) for faster generation. For latency-sensitive apps, check the TTFT comparison above.