Qwen: Qwen3 Max Thinking

qwen/qwen3-max-thinking

Qwen3 Max Thinking (Qwen) ranks #80 of 234 on the TryAii Score at $0.78/$3.9 per million input/output tokens, though DeepSeek V4 Flash 0423 matches it for $0.171 per million output tokens. Its best showing is #40 on IFBench.

Prompt $/1M

$0.780

Completion $/1M

$3.900

Context

262,144 tok

Best provider

24 tok/s · Alibaba

Specs

Model id: qwen/qwen3-max-thinking
Display name: Qwen: Qwen3 Max Thinking
Modality: text->text
Tokenizer: Qwen
Instruct type: —
Context length: 262,144
Max completion: 65,536
Prompt $/1M: $0.780
Completion $/1M: $3.900
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Alibabafastest	24	936 ms	1,021 ms
qwenfastest	—	—	—
Artificial Analysis	0	0 ms	—