Safety model for policy screening, moderation, and risk-aware routing workflows
Specification
most-agreed values
Context
128K
Max output
8K
Released
2026-06-02
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
free
Output
free
Cache read
$0.025
Available from 8 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kilo · free | free | free | — | — | 128K | 8K | — |
| nvidia | free | free | — | — | 128K | 8K | — |
| openrouter · free | free | free | — | — | 128K | 8K | — |
| requesty | free | free | — | — | 131K | 8K | — |
| nano-gpt | $0.05 | $0.15 | $0.025 | — | 131K | 33K | — |
| vultr | $0.05 | $0.15 | — | — | 131K | 8K | — |
| kilo | $0.20 | $0.20 | — | — | 131K | 118K | — |
| openrouter | $0.20 | $0.20 | — | — | 131K | 118K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | openrouter · free | Input | free |
| 2026-09-06 | openrouter · free | Input | free |
| 2026-10-10 | openrouter · free | Input | free |
| 2026-09-02 | openrouter · free | Output | free |
| 2026-09-06 | openrouter · free | Output | free |
| 2026-10-10 | openrouter · free | Output | free |
| 2026-09-04 | openrouter | Input | $0.20 |
| 2026-09-06 | openrouter | Input | $0.20 |
| 2026-10-10 | openrouter | Input | $0.20 |
| 2026-09-04 | openrouter | Output | $0.20 |
| 2026-09-06 | openrouter | Output | $0.20 |
| 2026-10-10 | openrouter | Output | $0.20 |
More from NVIDIA
most-hosted first