Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Specification
most-agreed values
Context
131K
Max output
41K
Released
2026-08-14
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.99
Output
$1.49
Cache read
$0.99
Quality
1 benchmark · 1 source
Composite
63rd
percentile of 344 scored models
Rank
128 / 344
±0.56 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
general47th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| LiveBench | 75.8 | default · 23 runs | LiveBench | 2026-06-25 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| neuralwatt | $0.45 | $3.20 | $0.25 | — | 262K | 131K | — |
| venice | $0.45 | $3.20 | — | — | 262K | 66K | — |
| cerebras | $0.99 | $1.49 | $0.99 | — | 131K 66K | 41K 33K | — |
| tempr | $0.99 | $1.49 | — | — | 131K | 41K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-07 | cerebras | Input | $0.99 |
| 2026-09-13 | cerebras | Input | $0.99 |
| 2026-09-07 | cerebras | Output | $1.49 |
| 2026-09-13 | cerebras | Output | $1.49 |
Other listings of this model
this page is one of them
The corpus files Qwen3.8 27B under several keys. This page is the qwen-3-8-27b listing. The full record — every host, every price and every benchmark score — is on the main Qwen3.8 27B page.
More from Alibaba
most-hosted first