qwen
Qwen: Qwen-Max
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...
Quality Score
71/100
composite of price, context, capability
Input Price
$1.04
per 1M tokens
Output Price
$4.16
per 1M tokens
Context Window
32,768
tokens
- Model ID
- qwen/qwen-max
- Vendor
- qwen
- Tokenizer
- Qwen
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 8,192 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
qwen
Qwen2.5 72B Instruct
$0.12 in / $0.39 out
32,768 ctx
73
qwen
Qwen: Qwen2.5 7B Instruct
$0.04 in / $0.10 out
32,768 ctx
74
qwen
Qwen: Qwen2.5 VL 72B Instruct
$0.25 in / $0.75 out
32,000 ctx
68
qwen
Qwen: Qwen3 30B A3B
$0.08 in / $0.28 out
40,960 ctx
79
qwen
Qwen: Qwen3 8B
$0.05 in / $0.40 out
40,960 ctx
79
qwen
Qwen: Qwen3 14B
$0.06 in / $0.24 out
40,960 ctx
80