Efficient Qwen model for fast chat, extraction, and high-volume workloads
Specification
alibaba listing
Context
1M
Max output
16K
Released
2024-11-01
Knowledge cutoff
2024-04
Retires
—
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · alibaba list price
Input
$0.05
Output
$0.20
Cache read
$0.025
Quality
3 benchmarks · 1 source
Composite
27th
percentile of 334 scored models
Rank
244 / 334
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning19th1/4 bench
math30th2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 56.2 ±1.1 | default | Epoch AI | 2025-04-07 |
| GPQA diamond | 41.8 ±2.6 | default | Epoch AI | 2025-04-07 |
| OTIS Mock AIME 2024-2025 | 6.1 ±2.2 | default | Epoch AI | 2025-04-07 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 9 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| alibabavendor | $0.05 | $0.20 | — | — | 1M | 16K | — |
| ofox | $0.043 | $0.09 | $0.0086 | — | 128K | 16K | — |
| alibaba-cn | $0.044 | $0.087 | — | — | 1M | 16K | — |
| dashscope · dashscope | $0.05 | $0.20 | — | — | 129K 1M | 16K 8K | — |
| nano-gpt | $0.05 | $0.2006 | $0.025 | — | 1M | 8K | — |
| ofox · bailian | $0.05 | $0.09 | $0.0086 | — | 128K | 16K | — |
| qwen_ai_platform · qwen-ai-platform | $0.05 | $0.20 | — | — | 129K 1M | 16K 8K | — |
| qwencloud · qwencloud | $0.05 | $0.20 | — | — | 129K 1M | 16K 8K | — |
| qiniu-ai | — | — | — | — | 1M | 4K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-11 | ofox | Input | $0.05 |
| 2026-09-12 | ofox | Input | $0.043 |
More from Alibaba
most-hosted first