Alibaba Qwen logo

Qwen3 235B-A22B

alibaba/qwen3-235b-a22b

Large open Qwen MoE for multilingual reasoning, coding, and tool use

Source-linkedqwenOpen weightsReleased 2025-04
Report data
Context window131.072K
Maximum output16.384K
Provider offers4
Knowledge cutoff2025-04
Capabilities

What this model supports

ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
Creator
Alibaba Qwen
Family
qwen
Modalities
Text
License
Not documented
Release date
2025-04
Model ID
alibaba/qwen3-235b-a22b
Market availability

Provider pricing

Report price →
Providers offering Qwen3 235B-A22B
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
Hugging FaceQwen/Qwen3-235B-A22B40.96K$0.200$0.800R T S
View
{
  "input": 0.2,
  "output": 0.8
}
Alibaba (China)qwen3-235b-a22b131.072K$0.287$1.147R T ·
View
{
  "input": 0.287,
  "output": 1.147,
  "reasoning": 2.868
}
OpenRouterqwen/qwen3-235b-a22b131.072K$0.455$1.820R T ·
View
{
  "input": 0.455,
  "output": 1.82
}
Alibabaqwen3-235b-a22b131.072K$0.700$2.800R T ·
View
{
  "input": 0.7,
  "output": 2.8,
  "reasoning": 8.4
}
Evidence

Published benchmark results

Aider Polyglot vs top 8 models
GPT-5
88.0
o3-pro
84.9
Gemini 2.5 Pro
83.1
o3
81.3
DeepSeek Reasoner
74.2
Claude Opus 4
72.0
o4-mini
72.0
Qwen3 235B-A22B
59.6
SWE-Bench Pro vs top 8 models
Claude Fable 5
80.3
Claude Opus 4.8
69.2
Grok 4.5
64.7
GPT-5.6 Sol
64.6
Claude Opus 4.7
64.3
GPT-5.6 Terra
63.4
Claude Sonnet 5
63.2
Qwen3 235B-A22B
21.4