MiniMax M2-her is cheaper than Llama 3.1 70B (Instruct) at $0.3/M vs $0.59/M input tokens.
| Spec | Llama 3.1 70B (Instruct) | MiniMax M2-her |
|---|---|---|
| Input price | $0.59/M tokens | $0.3/M tokens |
| Output price | $0.79/M tokens | $1.2/M tokens |
| Context window | 128K tokens | 66K tokens |
| Released | Jul 2024 | Jan 2026 |
Not enough votes to call it. On the specs, nothing separates them.
MiniMax M2-her wins input (2.0× cheaper)·Llama 3.1 70B (Instruct) wins output (1.5× cheaper)
MiniMax M2-her uses 96.5x more emoji
MiniMax M2-her is cheaper than Llama 3.1 70B (Instruct) at $0.3/M vs $0.59/M input tokens.
| Spec | Llama 3.1 70B (Instruct) | MiniMax M2-her |
|---|---|---|
| Input price | $0.59/M tokens | $0.3/M tokens |
| Output price | $0.79/M tokens | $1.2/M tokens |
| Context window | 128K tokens | 66K tokens |
| Released | Jul 2024 | Jan 2026 |
Not enough votes to call it. On the specs, nothing separates them.
MiniMax M2-her wins input (2.0× cheaper)·Llama 3.1 70B (Instruct) wins output (1.5× cheaper)
MiniMax M2-her uses 96.5x more emoji