Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Specification
most-agreed values
Context
131K
Max output
16K
Released
—
Knowledge cutoff
2025-03-31
Retires
—
Open weights
—
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.12
Output
$0.24
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openrouter | $0.12 | $0.24 | — | — | 131K | 16K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | openrouter | Input | $0.12 |
| 2026-09-03 | openrouter | Input | $0.2275 |
| 2026-09-04 | openrouter | Input | $0.12 |
| 2026-09-08 | openrouter | Input | $0.2275 |
| 2026-09-14 | openrouter | Input | $0.12 |
| 2026-09-02 | openrouter | Output | $0.24 |
| 2026-09-03 | openrouter | Output | $0.91 |
| 2026-09-04 | openrouter | Output | $0.24 |
| 2026-09-08 | openrouter | Output | $0.91 |
| 2026-09-14 | openrouter | Output | $0.24 |
More from Alibaba
most-hosted first