Meta-Llama-3-70B-Instruct vs Hy3 preview
Hy3 preview is cheaper on output tokens, while Hy3 preview offers a larger context window. Choose Meta-Llama-3-70B-Instruct or Hy3 preview based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Meta-Llama-3-70B-Instruct | Hy3 preview |
|---|---|---|
| Provider | Azure | Tencent TokenHub |
| Input / 1M tokens | $2.68 | $0.00 |
| Output / 1M tokens | $3.54 | $0.00 |
| Context window | 8K | 256K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Apr 2024 | Apr 2026 |
| GPQA Diamond score | 40.6 | — |
| LMArena (Chatbot Arena) Elo score | — | 1401 |
| LMArena WebDev Elo score | — | 1357 |
FAQ
Is Meta-Llama-3-70B-Instruct or Hy3 preview cheaper?
Hy3 preview is cheaper on output tokens ($0.00 vs $3.54 per 1M).
Which has the larger context window, Meta-Llama-3-70B-Instruct or Hy3 preview?
Hy3 preview has the larger context window (256K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.