qwen3.8
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total.
text → text · made by Alibaba
$2→$6per Mtok in / out
DigitalOcean
Sold by 5 ways
| Seller | Lane | Rate |
|---|---|---|
| DigitalOcean 0 ways | $2per Mtok in$6per Mtok out$0.2per Mtok cached | |
| DigitalOcean cloudnot on the seller's list today | standard | $2per Mtok in$6per Mtok out$0.2per Mtok cachedmodels.dev · read 2026-08-30 |
| ElectronHub 0 ways | $2per Mtok in$6per Mtok out | |
| ElectronHub aggregatornot on the seller's list today | standard | $2per Mtok in$6per Mtok outapi.electronhub.ai · read 2026-08-29 |
| Fireworks AI 0 ways | $2per Mtok in$6per Mtok out$0.25per Mtok cached | |
| Fireworks AI aggregatornot on the seller's list today | standard | $2per Mtok in$6per Mtok out$0.25per Mtok cachedraw.githubusercontent.com · read 2026-08-29 |
| Requesty aggregator | deepinfra | $2per Mtok in$6per Mtok out$0.2per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| PPIO 0 ways | $12per Mtok in$36per Mtok out | |
| PPIO aggregatornot on the seller's list today | standard | $12per Mtok in$36per Mtok outapi.ppinfra.com · read 2026-08-30 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 30thof 46 | LMArena · Agent | Net Improvement (%) | 3.3 |
About
qwen3.8 — a text model from Alibaba, placed 30th of 46 on LMArena · Agent.
It takes text and returns text, with a context window of 262,144 tokens. It was published in July 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under extract and agents. It stands 30th of 46 on LMArena · Agent.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 262,144 tokens
- Published
- July 2026
- Licence
- not read
- Boards
- 1
- Best place
- 30th of 46 — LMArena · Agent
Known as 1 name
deepinfra/qwen3.8