Qwen: QwQ 32B
qwen/qwq-32b
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...
Prompt $/1M
$0.150
Completion $/1M
$0.580
Context
131,072 tok
Best provider
31 tok/s · SiliconFlow
Specs
- Model id
- qwen/qwq-32b
- Display name
- Qwen: QwQ 32B
- Modality
- text->text
- Tokenizer
- Qwen
- Instruct type
- qwq
- Context length
- 131,072
- Max completion
- 131,072
- Prompt $/1M
- $0.150
- Completion $/1M
- $0.580
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- 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 |
|---|---|
| SiliconFlowfastest | 31 |