Llama 3.1 405B
retiredMeta · Released Jul 2024
Largest open-weight model at launch — GPT-4-class quality that anchored hosted pricing expectations lower.
Input / 1M
$3.00
Output / 1M
$3.00
Cached input / 1M
—
Context window
128K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 23 Jul 2024 | $3.00 | $3.00 | — | Representative hosted rate (Together AI); varies by provider | pricepertoken.com |