Llama 3.1 70B (Instruct) is cheaper than Mercury at $0.59/M vs $10/M input tokens.
| Spec | Llama 3.1 70B (Instruct) | Mercury |
|---|---|---|
| Input price | $0.59/M tokens | $10/M tokens |
| Output price | $0.79/M tokens | $10/M tokens |
| Context window | 128K tokens | 32K tokens |
| Parameters | 70B | Not disclosed |
| Weights | Open | — |
| Free API (OpenRouter) | No | No |
| Released | Jul 2024 | Jun 2025 |
| HumanEval | 80.5% | 90.0% |
Not enough votes to call it. On the specs, Llama 3.1 70B (Instruct) has the edge: bigger model tier, bigger context window, major provider backing.
Llama 3.1 70B (Instruct) costs 13x less per token.
Reviewing agent-written code?See a Brief PR report
Llama 3.1 70B (Instruct) is cheaper on both: 17× input, 13× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 11 Sep 2026.
Mercury uses 2.8x more emoji