Llama 3.1 family
Meta's open-weight Llama 3.1 line at three sizes.
Llama 3.1 ships at 405B, 70B, and 8B parameter counts. Open weights mean you can self-host or pick whichever inference provider gets you the best $/token; quality and capability climb with parameter count.
Specifications side-by-side
| Spec | Meta: Llama 3.1 70B Instruct | Meta: Llama 3.1 8B Instruct |
|---|---|---|
| Provider | meta-llama | meta-llama |
| Context | 131K | 16K |
| Max output | 16,384 | 16,384 |
| Input $/Mtok | $0.40 | $0.02 |
| Output $/Mtok | $0.40 | $0.05 |
| Modalities | text | text |
| License | proprietary | proprietary |
| Released | 2024-07-23 | 2024-07-23 |