Qwen Models
Qwen logo

Qwen-Max

by Qwen

Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion tokens and further post-trained with curated Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) methodologies. The parameter count is unknown.

Chat with Qwen-Max
Input Price$1.20/1M tokens
Output Price$6.00/1M tokens
Intelligence31.3
Coding26.4

Specifications

Technical details and pricing.

ProviderQwen
Context Window32,768 tokens
Release DateSep 23, 2025
ModalitiesText

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA76.4%
MMLU Pro84.1%
HLE11.1%
LiveCodeBench76.7%
AIME 202580.7%
SciCode38.3%
LCR46.7%
IFBench44.1%
Tau274.3%
TerminalBench Hard20.5%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Qwen-Max good for?

Use Qwen-Max for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Qwen-Max cost?

Pricing is based on usage. Current rates are $1.20/1M tokens for input and $6.00/1M tokens for output.

Can I try Qwen-Max for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Qwen-Max support images or audio?

Qwen-Max focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.