Meta-llama
llama-3.1-405b
Made by Meta AI. Released 2024-07-23. Accessibility not recorded. Cheapest standard rate we hold: $3.50 per million output tokens, no context split.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| standard | text | $3.50 | $3.50 | — | licensed-index |
per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.
What it scores, by house
| Benchmark | House | Score | Evaluated | Scaffold |
|---|---|---|---|---|
| arc ai2 | collected by Epoch AI | 1.0 | — | — |
| bbh | collected by Epoch AI | 0.8 | — | — |
| hella swag | collected by Epoch AI | 0.9 | — | — |
| mmlu | collected by Epoch AI | 0.8 | — | — |
| piqa | collected by Epoch AI | 0.9 | — | — |
| trivia qa | collected by Epoch AI | 0.8 | — | — |
| wino grande | collected by Epoch AI | 0.9 | — | — |
These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.
Every rate we hold · Why there is no single best model · Everything from Meta-llama