Small open Qwen2.5 instruction model for chat, structured output, and tool use
Specification
most-agreed values
Context
33K
Max output
8K
Released
2024-09-19
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.04
Output
$0.10
Quality
2 benchmarks · 1 source
Composite
11th
percentile of 344 scored models
Rank
306 / 344
±0.09 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
reasoning13th1/4 bench
math5th1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 35.5 ±2.3 | default | Epoch AI | 2026-08-30 |
| OTIS Mock AIME 2024-2025 | 2.5 ±0.9 | default | Epoch AI | 2026-08-30 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 6 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| siliconflow-cn | free | free | — | — | 33K | 4K | — |
| deepinfra | $0.04 | $0.10 | — | — | 33K | 33K | — |
| edenai | $0.04 | $0.10 | — | — | 33K | 8K | — |
| siliconflow | $0.05 | $0.05 | — | — | 33K | 4K | — |
| novita | $0.07 | $0.07 | — | — | 32K | 8K | — |
| fireworks_ai | $0.20 | $0.20 | — | — | 33K | 33K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | siliconflow-cn | Input | $0.05 |
| 2026-10-22 | siliconflow-cn | Input | free |
| 2026-09-02 | siliconflow-cn | Output | $0.05 |
| 2026-10-22 | siliconflow-cn | Output | free |
More from Alibaba
most-hosted first