Open Llama instruction model for multilingual chat, reasoning, and coding
Specification
most-agreed values
Context
131K
Max output
33K
Released
2024-12-06
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.59
Output
$0.79
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| inferenceapis · inferenceapis | $0.20 | $0.50 | — | — | 131K | 131K | — |
| abacus | $0.59 | $0.79 | — | — | 128K | 33K | — |
| groq | $0.59 | $0.79 | — | — | 131K | 33K | — |
| helicone | $0.59 | $0.79 | — | — | 131K | 33K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | groq | Input | $0.59 |
| 2026-09-23 | groq | Input | $0.59 |
| 2026-09-02 | groq | Output | $0.79 |
| 2026-09-23 | groq | Output | $0.79 |
Other listings of this model
this page is one of them
The corpus files Llama 3.3 70B under several keys. This page is the llama-3-3-70b-versatile listing. The full record — every host, every price and every benchmark score — is on the main Llama 3.3 70B page.
More from Meta
most-hosted first