Qwen / Alibaba

About Qwen / Alibaba

Qwen Team The Qwen team aims at chasing artificial general intelligence and now focuses on building generalist models, including large language models and large multimodal models. We embrace opensource and previously we have released the Qwen model series, including the language models (Qwen), expert models (Qwen-Coder and Qwen-Math), and multimodal models (Qwen-VL and Qwen-Audio). Additionally, we have built web service and APP for users to benefit from the assistance of Qwen for your daily work and life.

The Qwen team aims at chasing artificial general intelligence and now focuses on building generalist models, including large language models and large multimodal models. We embrace opensource and previously we have released the Qwen model series, including the language models (Qwen), expert models (Qwen-Coder and Qwen-Math), and multimodal models (Qwen-VL and Qwen-Audio). Additionally, we have built web service and APP for users to benefit from the assistance of Qwen for your daily work and life. We are a group of people with diverse talents and interests. Feel free to chat with us and welcome to join us!

In the following, we provide important links for you to refer to our opensource resources.

GITHUB MODELSCOPE HUGGING FACE KAGGLE

Website ↗Hugging Face ↗

Source ↗ · 2026-11-12T04:15:28.848605624Z

Transparency & Governance

  • Foundation Model Transparency Index 2025 · 26 / 100 · Company disclosure assessment Source assessment ↗

450 indexed models

450 matching models

qwen3-max-thinking

cheaperInference/qwen3-max-thinking

Context window
256,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Qwen 3 Max Thinking

vercelAIGatewayCatalog/alibaba/qwen3-max-thinking

Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release achieves an effective integration of thinking and non-thinking modes, resulting in a comprehensive and substantial improvement in the model’s overall performance. In thinking mode, th

Context window
256,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Qwen3 Next 80B A3B

awsBedrock/qwen.qwen3-next-80b-a3b

Input modalities
text
Output modalities
text

qwen3-next-80b-a3b-instruct

cheaperInference/qwen3-next-80b-a3b-instruct

Context window
256,000
Maximum output
262,114
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

qwen3-next-80b-a3b-thinking

cheaperInference/qwen3-next-80b-a3b-thinking

Context window
262,144
Maximum output
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Qwen3-Next-80B Instruct

vertexAI/publishers/qwen/models/qwen3-next-80b-a3b-instruct-maas@001

Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Qwen3-Next-80B Thinking

vertexAI/publishers/qwen/models/qwen3-next-80b-a3b-thinking-maas@001

Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

qwen3-omni-30b-a3b-thinking

cheaperInference/qwen3-omni-30b-a3b-thinking

Context window
65,536
Maximum output
16,384
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

Qwen3 Reranker 0.6B

qwen/qwen3-reranker-0.6b

Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores for retrieval and RAG pipelines. Supports 100+ languages with instruction-aware

Context window
32,768
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Inference prices

  • Published price : $0.01 / input_tokens_per_million · deepInfra ↗

Qwen3 Reranker 8B

qwen/qwen3-reranker-8b

Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware rerankin

Context window
40,960
Input modalities
text
Output modalities
rerank
Capabilities
rerank

Inference prices

  • Input tokens (per 1M) : $0.04 / input_tokens_per_million · siliconFlow ↗

Qwen3 VL 235B A22B

awsBedrock/qwen.qwen3-vl-235b-a22b

Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

qwen3-vl-235b-a22b-instruct

cheaperInference/qwen3-vl-235b-a22b-instruct

Context window
256,000
Maximum output
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, toolCalling, visionInput

Inference prices

Qwen3 VL 235B A22B Instruct

vercelAIGatewayCatalog/alibaba/qwen3-vl-instruct

The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and spatial perception. Its visual perception and recognition capabilities have significantly improved, supporting the understanding of ultra-long videos, and its OCR functionality has und

Context window
262,144
Maximum output
262,144
Input modalities
text, image
Output modalities
text

Qwen3-VL-235B-A22B-Instruct-FP8

vertexAI/publishers/qwen/models/qwen3-vl@qwen3-vl-235b-a22b-instruct-fp8

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Qwen3 VL 235B A22B Thinking

vercelAIGatewayCatalog/alibaba/qwen3-235b-a22b-thinking

Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have

Context window
131,072
Maximum output
32,768
Input modalities
text, image, pdf
Output modalities
text

Qwen3 VL 235B A22B Thinking

vercelAIGatewayCatalog/alibaba/qwen3-vl-thinking

Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning. Visual perception and recognition abilities have been comprehensively improved, and OCR capabilities have

Context window
131,072
Maximum output
32,768
Input modalities
text, image, pdf
Output modalities
text

Qwen3-VL-235B-A22B-Thinking-FP8

vertexAI/publishers/qwen/models/qwen3-vl@qwen3-vl-235b-a22b-thinking-fp8

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Qwen3-VL-2B-Instruct-FP8

vertexAI/publishers/qwen/models/qwen3-vl@qwen3-vl-2b-instruct-fp8

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace