Llama 3 70B Instruct vs Llama 3.2 90B Vision Instruct
Llama 3.2 90B Vision Instruct is cheaper on output tokens, while Llama 3.2 90B Vision Instruct offers a larger context window. Choose Llama 3 70B Instruct or Llama 3.2 90B Vision Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Llama 3 70B Instruct | Llama 3.2 90B Vision Instruct |
|---|---|---|
| Provider | DevPass (LLM Gateway) | Vercel AI Gateway |
| Input / 1M tokens | $0.51 | $0.72 |
| Output / 1M tokens | $0.74 | $0.72 |
| Context window | 8K | 128K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Apr 2024 | Sep 2024 |
| LMArena (Chatbot Arena) Elo score | 1221 | — |
| GPQA Diamond score | — | 41.0 |
FAQ
Is Llama 3 70B Instruct or Llama 3.2 90B Vision Instruct cheaper?
Llama 3.2 90B Vision Instruct is cheaper on output tokens ($0.72 vs $0.74 per 1M).
Which has the larger context window, Llama 3 70B Instruct or Llama 3.2 90B Vision Instruct?
Llama 3.2 90B Vision Instruct 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.