Google Gemma 4 31B vs OpenAI GPT-5 Nano
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- GPT-5 Nano is 1.8× cheaper at a typical mix of 3 input tokens per output token.
- GPT-5 Nano accepts longer prompts: 400K vs 262K tokens.
- Gemma 4 31B is the newer model (released 2026-04-02).
| Gemma 4 31B | GPT-5 Nano | |
|---|---|---|
| Vendor | OpenAI | |
| Released | 2026-04-02 | 2025-08-07 |
| Input / 1M | $0.20 | $0.05 |
| Output / 1M | $0.40 | $0.40 |
| Cached input / 1M | — | $0.0050 |
| Blended / 1M (3:1) | $0.25 | $0.138 |
| Context | 262K | 400K |
| Max output | 16K | 128K |
| Accepts | text, image, video | text, image, file |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 16 | 4 |
| Cheapest provider, output | $0.34 | $0.40 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Gemma 4 31B
$18.00 per month$0.60 per day
GPT-5 Nano
$9.00 per month$0.30 per day
GPT-5 Nano saves $9.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Gemma 4 31B with