Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Gemma 4 31B (Non-reasoning) | GPT-4.1 nano |
|---|---|---|
| Input ($/M tokens) | $0.14 | $0.1 |
| Output ($/M tokens) | $0.4 | $0.4 |
Verdict. Gemma 4 31B (Non-reasoning) wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, GPT-4.1 nano is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). GPT-4.1 nano makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Gemma 4 31B (Non-reasoning) is strongest on Coding Index (33.2), Intelligence Index (13.9). GPT-4.1 nano leads on Coding Index (11.1), Intelligence Index (7.8).
Speed. On throughput, GPT-4.1 nano generates tokens at 187 tok/s versus 46 tok/s — about 75% faster. On time-to-first-token, GPT-4.1 nano responds in 720ms vs 1890ms, which matters most for chat-style UIs.
Provider. Google and OpenAI sell to overlapping but distinct developer audiences: Google tends to ship frontier reasoning models with premium positioning, while OpenAI often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Gemma 4 31B (Non-reasoning) costs $10.20 ($122/year); GPT-4.1 nano costs $9.00 ($108/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Gemma 4 31B (Non-reasoning) ≈ $1.50/run, GPT-4.1 nano ≈ $1.30/run. At agent/realtime scale (200M input / 100M output per million requests): Gemma 4 31B (Non-reasoning) ≈ $68/run, GPT-4.1 nano ≈ $60/run. GPT-4.1 nano becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
GPT-4.1 nano is cheaper overall. Its blended price (3:1 input/output ratio) is $0.17/M tokens vs $0.20/M for Gemma 4 31B (Non-reasoning).
Gemma 4 31B (Non-reasoning) wins 2 out of 12 benchmarks compared to 0 for GPT-4.1 nano. See the detailed benchmark chart above for per-category results.
GPT-4.1 nano generates tokens faster at 187 tok/s vs 46 tok/s. However, GPT-4.1 nano has lower time-to-first-token (0.72s vs 1.89s).
Choose based on your priorities: GPT-4.1 nano for lower cost, Gemma 4 31B (Non-reasoning) for stronger benchmark performance, and GPT-4.1 nano for faster generation. For latency-sensitive apps, check the TTFT comparison above.