Skip to content
Dashboard

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is the open-weight release of Alibaba Cloud's Qwen 3.8 flagship, a 2.4-trillion-parameter Mixture-of-Experts model with 95B active per token and a context window of 262.1K tokens. Your use is subject to Alibaba Cloud's Terms & Privacy Policies.

ReasoningTool UseImplicit Caching
import { streamText } from 'ai'
const result = streamText({
model: 'alibaba/qwen3.8-2.4t-a95b',
prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Release Date
256K131K
1.4s
62tps
$1.65/M
$4.95/M
Read:$0.12/M
Write:
08/03/2026
262K131K
1.5s
216tps
$2/M
$6/M
Read:$0.25/M
Write:
08/03/2026
262K131K
1.7s
71tps
$2/M
$6/M
Read:$0.25/M
Write:$2.5/M
08/03/2026
262K131K
1.6s
56tps
$2/M
$6/M
Read:$0.25/M
Write:
08/03/2026
262K131K
1.0s
$2/M
$6/M
Read:$0.25/M
Write:
08/03/2026
262K131K
1.5s
164tps
$2/M
$6/M
Read:$0.2/M
Write:
08/03/2026