Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-5.4 nano (medium) | DeepSeek V3 0324 |
|---|---|---|
| Input ($/M tokens) | $0.2 | $1.195 |
| Output ($/M tokens) | $1.25 | $1.25 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.4 nano (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.46/M tokens vs $1.21/M for DeepSeek V3 0324.
GPT-5.4 nano (medium) wins 7 out of 12 benchmarks compared to 5 for DeepSeek V3 0324. See the detailed benchmark chart above for per-category results.
GPT-5.4 nano (medium) generates tokens faster at 153 tok/s vs 0 tok/s. However, DeepSeek V3 0324 has lower time-to-first-token (0.00s vs 3.88s).
Choose based on your priorities: GPT-5.4 nano (medium) for lower cost, GPT-5.4 nano (medium) for stronger benchmark performance, and GPT-5.4 nano (medium) for faster generation. For latency-sensitive apps, check the TTFT comparison above.