Qwen3-235B-A22B-Thinking-2507

Released
2025-07-25
Last refreshed
2026-10-19
Status
Researched 1d ago
Open sourceCommercial use: permittedAgentsJSON / Tool useReasoning
Alibaba releases · 54 in the last 12 months · this family litChangelog →
Specifications
Family
Qwen3
Released
2025-07-25
Parameters
235B-A22B
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
$3.00
Input / 1M
$0.650

Cheapest of 2 routes · Together AI

About

Qwen3-235B-A22B-Thinking-2507 is Alibaba's thinking-mode MoE (22B active / 235B total) post-train of Qwen3-235B-A22B. Apache-2.0 open weights on HF. Thinking-only mode. HF README: native context 262,144 (OR catalog lists 128000 — conflict → context/maxOut blanked on model row). DashScope id qwen3-235b-a22b-thinking-2507.

Providers(2)

Compare all 2

Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Together AI$0.650$3.00
Serverless
OpenRouter$0.450$3.50
Serverless

Available via routers & gateways(1)

Capabilities

ReasoningJSON / Tool use

Benchmark peer barsfor Agents

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

Qwen3-235B-A22B-Thinking-2507qwen3-235b-a22b-thinking-2507qwen/qwen3-235b-a22b-thinking-2507