Qwen: Qwen-Max
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...
Prompt $/1M
$1.040
Completion $/1M
$4.160
Context
32,768 tok
Best provider
39 tok/s · Alibaba
Specs
- Model id
- qwen/qwen-max
- Display name
- Qwen: Qwen-Max
- Modality
- text->text
- Tokenizer
- Qwen
- Instruct type
- —
- Context length
- 32,768
- Max completion
- 8,192
- Prompt $/1M
- $1.040
- Completion $/1M
- $4.160
- 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 |
|---|---|
| Alibabafastest | 39 |
| qwenfastest | — |