Qwen instruction model for multilingual chat, reasoning, and tool use
Specification
most-agreed values
Context
33K
Max output
16K
Released
2025-01-01
Knowledge cutoff
2024-07
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.287
Output
$0.861
Rate limits
Requests per minute
300
Quality
2 benchmarks · 1 source
Composite
55th
percentile of 344 scored models
Rank
157 / 344
±0.09 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
reasoning56th1/4 bench
math56th1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6 ±6.2 | default | Epoch AI | 2026-08-28 |
| GPQA diamond | 64.1 ±2.8 | default | Epoch AI | 2026-08-28 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nscale | $0.15 | $0.15 | — | — | — | — | — |
| deepinfra | $0.27 | $0.27 | — | — | 131K | 131K | — |
| alibaba-cn | $0.287 | $0.861 | — | — | 33K | 16K | — |
| novita | $0.30 | $0.30 | — | — | 64K | 32K | — |
| cloudflare | $0.497 | $4.881 | — | — | 80K | 80K | — |
| cloudflare-workers-ai · cf | $0.497 | $4.881 | — | — | 80K | 80K | — |
| fireworks_ai | $0.90 | $0.90 | — | — | 131K | 131K | — |
More from DeepSeek
most-hosted first