Qwen3 Max is open-source and can be self-hosted at no per-token cost. Third-party providers may offer free rate-limited access.

How much does Qwen3 Max cost?

Qwen3 Max costs $0.78 per million input tokens and $3.9 per million output tokens via the standard API.

What is Qwen3 Max's context window?

Qwen3 Max supports a context window of 262K tokens.

Alibaba · Released Apr 29, 2025

Open SourcereasoningcodingCompare this model

$0.78

Input price / MTok

#10 of 27

$3.9

Output price / MTok

#11 of 27

262K

Context window

#20 of 28

Tokens / sec

#18 of 21

76.4

GPQA Diamond

#16 of 19

AIME 2025

#9 of 10

Qwen3 Max is a open-source language model from Alibaba, released on Apr 29, 2025.

At $0.78 input and $3.9 output per million tokens, it ranks #10 of 27 for input price, placing it mid-range on input cost.

Its context window of 262K tokens ranks #20 of 28 for context depth in this dataset.

It targets reasoning, coding workloads.

Throughput is measured at 66 tokens per second (ranked #18 of 21 for throughput).

Apache 2.0 open weights; 235B total / 22B active MoE.

Benchmark	Score	Max	%	Rank	Source
GPQA Diamond	76.4	100	76.4%	#16/19	Alibaba Qwen Team (self-reported on qwen...
AIME 2025	75	100	75.0%	#9/10	Alibaba Qwen Team (self-reported on qwen...

Models with the most shared benchmark coverage and closest scores to Qwen3 Max.

Qwen3 Max

Gemini 2.5 Flash

Qwen3.7 Max

Gemini 2.5 Pro

o4-mini

GPQA Diamond#16 of 19

Graduate-level science reasoning

AIME 2025#9 of 10

Advanced math competition problems

Compare Qwen3 Max side by side

Pre-filled with 5 similar models