Skip to content
Dashboard

Qwen3 Next 80B A3B Thinking

Qwen3 Next 80B A3B Thinking is a hybrid Transformer-Mamba reasoning model that combines 80 billion total parameters (3B active per token) with a dedicated thinking mode, achieving strong results on AIME25 while supporting ultra-long contexts of 262.1K tokens. Your use subject to Alibaba Cloud's Terms & Privacy Policies.

ReasoningTool Use
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'alibaba/qwen3-next-80b-a3b-thinking',
prompt: 'Why is the sky blue?'
})

More models by Alibaba Cloud

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
991K
2.3s
194tps
$0.03/M
$0.13/M
Read:
$0.01/M
Write:
$0.04/M
+2
alibaba logo
07/28/2026
1M
2.2s
379tps
$0.32/M
$1.28/M
Read:$0.08/M
Write:$0.5/M
+2
alibaba logo
fireworks logo
togetherai logo
06/02/2026
991K
2.3s
55tps
$2.50/M
$7.50/M
Read:$0.5/M
Write:$3.13/M
alibaba logo
05/21/2026
1M
1.5s
178tps
$0.10/M
$0.40/M
Read:$0.0/M
Write:$0.13/M
+1
alibaba logo
02/24/2026
33K
$0.01/M
deepinfra logo
11/14/2025
262K
0.8s
49tps
$0.20/M
$0.88/M
Read:$0.11/M
Write:
alibaba logo
deepinfra logo
09/23/2025