Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | GPT-5.4 mini (Non-Reasoning) |
|---|---|---|
| Input ($/M tokens) | $0 | $0.75 |
| Output ($/M tokens) | $0 | $4.5 |
Data from Artificial Analysis API — 12 benchmarks
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $1.69/M for GPT-5.4 mini (Non-Reasoning).
GPT-5.4 mini (Non-Reasoning) wins 7 out of 12 benchmarks compared to 3 for DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning). See the detailed benchmark chart above for per-category results.
GPT-5.4 mini (Non-Reasoning) generates tokens faster at 202 tok/s vs 0 tok/s. DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) also has lower time-to-first-token (0.00s vs 0.45s).
Choose based on your priorities: DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) for lower cost, GPT-5.4 mini (Non-Reasoning) for stronger benchmark performance, and GPT-5.4 mini (Non-Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.