Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
Specification
most-agreed values
Context
41K
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
$0.50
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openrouter | $0.12 | $0.50 | — | — | 41K | 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 |
| 2026-09-29 | openrouter | Input | $0.13 |
| 2026-10-01 | openrouter | Input | $0.12 |
| 2026-09-02 | openrouter | Output | $0.50 |
| 2026-09-29 | openrouter | Output | $0.52 |
| 2026-10-01 | openrouter | Output | $0.50 |
More from Alibaba
most-hosted first