Skip to content

Qwen3 Max Preview

Qwen3 Max Preview is Alibaba's early-access release of its trillion-parameter Qwen3-Max model, providing developers with ahead-of-schedule access to Qwen3-Max capabilities for evaluation and prototyping.

Tool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'alibaba/qwen3-max-preview',
prompt: 'Why is the sky blue?'
})

More models by Alibaba

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
240K
2.8s
81tps
$1.30/M
$7.80/M
Read:
$0.26/M
Write:
$1.63/M
alibaba logo
04/20/2026
1M
0.5s
109tps
$0.50/M
$3.00/M
Read:
$0.1/M
Write:
$0.63/M
alibaba logo
fireworks logo
04/02/2026
1M
1.4s
69tps
$0.10/M$0.40/M
Read:$0.0/M
Write:$0.13/M
alibaba logo
02/24/2026
1M
3.4s
56tps
$0.40/M
$2.40/M
Read:
$0.04/M
Write:
$0.5/M
alibaba logo
02/16/2026
262K
0.4s
68tps
$0.20/M$0.88/M
Read:$0.11/M
Write:
alibaba logo
deepinfra logo
novita logo
09/24/2025
262K
0.5s
108tps
$0.22/M$1.80/M
Read:$0.02/M
Write:
alibaba logo
deepinfra logo
novita logo
+1
04/01/2025