Qwen3-30B-A3B-Thinking-2507

Released
2025-07-29
Last refreshed
2026-11-18
Status
Researched today
Open sourceCommercial use: permittedRAGAgentsLong contextJSON / Tool use
Alibaba releases · 52 in the last 12 months · this family litChangelog →
Specifications
Family
Qwen3
Released
2025-07-29
Context
256K
Parameters
30.5B (3.3B active)
Architecture
Mixture of Experts
Specialization
reasoning
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$2.40
Input / 1M
$0.200

Cheapest of 1 route · FlexAI · cache read $0.030

Providers(1)

About

Qwen3-30B-A3B-Thinking-2507 is Alibaba Qwen’s thinking-mode mixture-of-experts model with 30.5 billion total parameters and 3.3 billion activated. It runs only in thinking mode, has a native context of 262,144 tokens, and publishes Apache-2.0 open weights on Hugging Face.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
FlexAI$0.200$2.40read $0.030
Serverless

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

Qwen3-30B-A3B-Thinking-2507qwen/qwen3-30b-a3b-thinking-2507