Sao10K Llama 3.1 Euryale 70B v2.2 vs TheDrummer Skyfall 36B V2
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
- Skyfall 36B V2 is 1.4× cheaper at a typical mix of 3 input tokens per output token.
- Llama 3.1 Euryale 70B v2.2 accepts longer prompts: 131K vs 33K tokens.
- Llama 3.1 Euryale 70B v2.2's best provider was more reliable over 24 h: 99.78% vs 98.9%.
- Skyfall 36B V2 is the newer model (released 2025-03-10).
| Llama 3.1 Euryale 70B v2.2 | Skyfall 36B V2 | |
|---|---|---|
| Vendor | Sao10K | TheDrummer |
| Released | 2024-08-28 | 2025-03-10 |
| Input / 1M | $0.85 | $0.55 |
| Output / 1M | $0.85 | $0.80 |
| Cached input / 1M | — | $0.25 |
| Blended / 1M (3:1) | $0.85 | $0.613 |
| Context | 131K | 33K |
| Max output | 16K | 29K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 1 |
| Cheapest provider, output | $0.85 | $0.80 |
| Best provider uptime, 24 h | 99.78% | 98.9% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | — |
Cost calculator
Llama 3.1 Euryale 70B v2.2
$63.75 per month$2.13 per day
Skyfall 36B V2
$45.00 per month$1.50 per day
Skyfall 36B V2 saves $18.75 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Llama 3.1 Euryale 70B v2.2 with
Compare Skyfall 36B V2 with