Qwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.
Specification
most-agreed values
Context
262K
Max output
33K
Released
2026-07-29
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.25
Output
$1.50
Cache read
$0.20
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt | $0.25 | $1.50 | $0.20 | — | 262K | 33K | — |
| nano-gpt · thinking | $0.25 | $1.50 | $0.20 | — | 262K | 33K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | nano-gpt | Cache read | $0.125 |
| 2026-09-15 | nano-gpt | Cache read | $0.20 |
| 2026-09-02 | nano-gpt · thinking | Cache read | $0.125 |
| 2026-09-15 | nano-gpt · thinking | Cache read | $0.20 |
More from Alibaba
most-hosted first