Inception Mercury 2.5 vs Poolside Laguna S 2.1
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 2.5 is 1.7× cheaper at a typical mix of 3 input tokens per output token.
- Laguna S 2.1 accepts longer prompts: 1M vs 260K tokens.
- Mercury 2.5 is the newer model (released 2026-09-08).
| Mercury 2.5 | Laguna S 2.1 | |
|---|---|---|
| Vendor | Inception | Poolside |
| Released | 2026-09-08 | 2026-07-21 |
| Input / 1M | $0.04 | $0.09 |
| Output / 1M | $0.15 | $0.18 |
| Cached input / 1M | $0.0040 | $0.0090 |
| Blended / 1M (3:1) | $0.068 | $0.113 |
| Context | 260K | 1M |
| Max output | 66K | 131K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 1 | 1 |
| Cheapest provider, output | $0.15 | $0.18 |
| Best provider uptime, 24 h | 99.93% | 99.93% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | — |
Cost calculator
Mercury 2.5
$4.65 per month$0.15 per day
Laguna S 2.1
$8.10 per month$0.27 per day
Mercury 2.5 saves $3.45 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Mercury 2.5 with