Mercury 2 is cheaper than Llama 3.1 70B (Instruct) at $0.25/M vs $0.59/M input tokens.
| Spec | Llama 3.1 70B (Instruct) | Mercury 2 |
|---|---|---|
| Input price | $0.59/M tokens | $0.25/M tokens |
| Output price | $0.79/M tokens | $0.75/M tokens |
| Context window | 128K tokens | 128K tokens |
| Released | Jul 2024 | Mar 2026 |
Not enough votes to call it. On the specs, Llama 3.1 70B (Instruct) has the edge: bigger model tier, major provider backing.
Mercury 2 is cheaper on both — 2.4× input, 1.1× output
Mercury 2 uses 8.2x more emoji
Mercury 2 is cheaper than Llama 3.1 70B (Instruct) at $0.25/M vs $0.59/M input tokens.
| Spec | Llama 3.1 70B (Instruct) | Mercury 2 |
|---|---|---|
| Input price | $0.59/M tokens | $0.25/M tokens |
| Output price | $0.79/M tokens | $0.75/M tokens |
| Context window | 128K tokens | 128K tokens |
| Released | Jul 2024 | Mar 2026 |
Not enough votes to call it. On the specs, Llama 3.1 70B (Instruct) has the edge: bigger model tier, major provider backing.
Mercury 2 is cheaper on both — 2.4× input, 1.1× output
Mercury 2 uses 8.2x more emoji