Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-5.4 nano (Non-Reasoning) | Gemma 4 E4B (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.2 | $0 |
| Output ($/M tokens) | $1.25 | $0 |
Data from Artificial Analysis API — 12 benchmarks
Gemma 4 E4B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.46/M for GPT-5.4 nano (Non-Reasoning).
GPT-5.4 nano (Non-Reasoning) wins 5 out of 12 benchmarks compared to 2 for Gemma 4 E4B (Non-reasoning). See the detailed benchmark chart above for per-category results.
GPT-5.4 nano (Non-Reasoning) generates tokens faster at 140 tok/s vs 0 tok/s. However, Gemma 4 E4B (Non-reasoning) has lower time-to-first-token (0.00s vs 0.54s).
Choose based on your priorities: Gemma 4 E4B (Non-reasoning) for lower cost, GPT-5.4 nano (Non-Reasoning) for stronger benchmark performance, and GPT-5.4 nano (Non-Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.