Specification
most-agreed values
Context
128K
Max output
2K
Released
—
Knowledge cutoff
—
Retires
2025-06-30
Open weights
—
Input
—
Output
—
Price
US dollars per million tokens · most-agreed
Input
$2.68
Output
$3.54
Available from 5 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| hyperbolic | $0.12 | $0.30 | — | — | 33K | 33K | — |
| nebius | $0.13 | $0.40 | — | — | 128K | 128K | — |
| deepinfra | $0.40 | $0.40 | — | — | 131K | 131K | — |
| ovhcloud · ovhcloud | $0.67 | $0.67 | — | — | 131K | 131K | — |
| azure_ai | $2.68 | $3.54 | — | — | 128K | 2K | 2025-06-30 |
More from Meta
most-hosted first