Skip to content
Dashboard

Qwen3.8 2.4T A95B

Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only. 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 headingMore models by Alibaba Cloud

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
2.9s
57tps
$2/M
$6/M
Read:$0.25/M
Write:$2.5/M
+1
alibaba logo
08/02/2026
991K
1.4s
111tps
$0.03/M+2 more
$0.13/M+2 more
Read:
$0.01/M+2 more
Write:
$0.04/M+2 more
+2
alibaba logo
07/28/2026
1M
2.1s
227tps
$0.40/M+1 more
$1.60/M+1 more
Read:
$0.08/M+1 more
Write:
$0.5/M+1 more
+2
alibaba logo
fireworks logo
06/02/2026
991K
1.5s
118tps
$2.50/M
$7.50/M
Read:$0.5/M
Write:$3.13/M
alibaba logo
05/21/2026
1M
1.7s
113tps
$0.50/M+1 more
$3/M+1 more
Read:
$0.1/M+1 more
Write:
$0.63/M+1 more
+1
alibaba logo
togetherai logo
04/02/2026
262K
0.5s
56tps
$0.20/M
$0.88/M
Read:$0.11/M
Write:
alibaba logo
deepinfra logo
09/23/2025