Google Gemma 4 31B vs Inception Mercury 3
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
- Mercury 3 is 1.5× cheaper at a typical mix of 3 input tokens per output token.
- Mercury 3 accepts longer prompts: 1M vs 262K tokens.
- Mercury 3 is the newer model (released 2026-10-16).
| Gemma 4 31B | Mercury 3 | |
|---|---|---|
| Vendor | Inception | |
| Released | 2026-04-02 | 2026-10-16 |
| Input / 1M | $0.20 | $0.10 |
| Output / 1M | $0.40 | $0.35 |
| Cached input / 1M | — | $0.01 |
| Blended / 1M (3:1) | $0.25 | $0.163 |
| Context | 262K | 1M |
| Max output | 16K | 131K |
| Accepts | text, image, video | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 16 | 1 |
| Cheapest provider, output | $0.34 | $0.35 |
| Best provider uptime, 24 h | 100% | 99.93% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
Gemma 4 31B
$18.00 per month$0.60 per day
Mercury 3
$11.25 per month$0.38 per day
Mercury 3 saves $6.75 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Gemma 4 31B with