Google Gemma 2 27B vs Mistral Saba
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
- Saba is 2.2× cheaper at a typical mix of 3 input tokens per output token.
- Saba accepts longer prompts: 33K vs 8K tokens.
- Saba is the newer model (released 2025-02-17).
| Gemma 2 27B | Saba | |
|---|---|---|
| Vendor | Mistral | |
| Released | 2024-07-13 | 2025-02-17 |
| Input / 1M | $0.65 | $0.20 |
| Output / 1M | $0.65 | $0.60 |
| Cached input / 1M | — | $0.02 |
| Blended / 1M (3:1) | $0.65 | $0.30 |
| Context | 8K | 33K |
| Max output | 2K | 26K |
| Accepts | text | text, file |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 3 |
| Cheapest provider, output | $0.65 | $0.60 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Gemma 2 27B
$48.75 per month$1.63 per day
Saba
$21.00 per month$0.70 per day
Saba saves $27.75 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Gemma 2 27B with