Qwen3-30B-A3B

Qwen3-30B-A3B is a mixture-of-experts model from Alibaba Cloud that activates only 3 billion of its 30 billion parameters per inference, outperforming QwQ-32B while running at a fraction of the compute cost. Your use subject to Alibaba Cloud's Terms & Privacy Policies.

ReasoningTool Use

Use with AI Gateway View docs

index.ts

import { streamText } from 'ai'

const result = streamText({
  model: 'alibaba/qwen-3-30b',
  prompt: 'Why is the sky blue?'
})

Overview About Providers Latency Uptime Status Similar FAQ

More models by Alibaba Cloud

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Release Date

alibaba/qwen3.7-flash

991K

1.8s

156tps

$0.03/M

$0.13/M

Read:

$0.01/M

Write:

$0.04/M

—

07/28/2026

alibaba/qwen3.7-plus

1.5s

201tps

$0.32/M

$1.28/M

Read:$0.08/M

Write:$0.5/M

—

06/02/2026

alibaba/qwen3.7-max

991K

2.5s

55tps

$2.50/M

$7.50/M

Read:$0.5/M

Write:$3.13/M

—

05/21/2026

alibaba/qwen3.5-flash

1.3s

163tps

$0.10/M

$0.40/M

Read:$0.0/M

Write:$0.13/M

—

02/24/2026

alibaba/qwen3-embedding-0.6b

33K

$0.01/M

—

11/14/2025

alibaba/qwen3-embedding-4b

33K

$0.02/M

—

06/05/2025

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Qwen3-30B-A3B

More models by Alibaba Cloud