Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | DeepSeek V3.1 Terminus (Reasoning) | GPT-5 mini (medium) |
|---|---|---|
| Input ($/M tokens) | $0.4 | $0.25 |
| Output ($/M tokens) | $2 | $2 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5 mini (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.69/M tokens vs $0.80/M for DeepSeek V3.1 Terminus (Reasoning).
DeepSeek V3.1 Terminus (Reasoning) wins 7 out of 12 benchmarks compared to 4 for GPT-5 mini (medium). See the detailed benchmark chart above for per-category results.
GPT-5 mini (medium) generates tokens faster at 82 tok/s vs 0 tok/s. DeepSeek V3.1 Terminus (Reasoning) also has lower time-to-first-token (0.00s vs 15.71s).
Choose based on your priorities: GPT-5 mini (medium) for lower cost, DeepSeek V3.1 Terminus (Reasoning) for stronger benchmark performance, and GPT-5 mini (medium) for faster generation. For latency-sensitive apps, check the TTFT comparison above.