Qwen3.8 2.4T A95B
AlibabaQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
In
$2.00
Out
$6.00
Blended
$3.00
Where to buy this model
5 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $2.00 | $6.00 | $3.00 | - | |
| ● Alibaba | $2.00 | $6.00 | $3.00 | +0% |
| ● SiliconFlow fp8 | $2.00 | $6.00 | $3.00 | +0% |
| ● Venice | $2.00 | $6.00 | $3.00 | +0% |
| $2.00 | $6.00 | $3.00 | +0% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 1.048576M
- max output
- 131K
- cache read /1M
- $0.25
- Family
- qwen
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Alibaba models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Qwen3 235B A22B Thinking 2507 | $0.45 | $3.5 | 128K |
| Qwen3.5 397B A17B | $0.5 | $3.6 | 262K |
| Qwen3.7 Max | $1.48 | $4.42 | 1M |
| Qwen3.8 Max (0902) | $2 | $6 | 1M |
| Qwen3.8 2.4T A95B · this model | $2 | $6 | 1.048576M |
| Qwen3.8 Max Prime | $4 | $12 | 1M |