Mercury 2 vs Llama 3 70B Instruct
Llama 3 70B Instruct is cheaper on output tokens, while Mercury 2 offers a larger context window. Choose Mercury 2 or Llama 3 70B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Mercury 2 | Llama 3 70B Instruct |
|---|---|---|
| Provider | Inception | DevPass (LLM Gateway) |
| Input / 1M tokens | $0.25 | $0.51 |
| Output / 1M tokens | $0.75 | $0.74 |
| Context window | 128K | 8K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Feb 2026 | Apr 2024 |
| LMArena (Chatbot Arena) Elo score | 1355 | 1221 |
| LMArena WebDev Elo score | 1171 | — |
FAQ
Is Mercury 2 or Llama 3 70B Instruct cheaper?
Llama 3 70B Instruct is cheaper on output tokens ($0.74 vs $0.75 per 1M).
Which has the larger context window, Mercury 2 or Llama 3 70B Instruct?
Mercury 2 has the larger context window (128K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.