Qwen: Qwen3 30B A3B Thinking 2507
qwen/qwen3-30b-a3b-thinking-2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Prompt $/1M
$0.130
Completion $/1M
$1.560
Context
131,072 tok
Best provider
98 tok/s · Alibaba
Specs
- Model id
- qwen/qwen3-30b-a3b-thinking-2507
- Display name
- Qwen: Qwen3 30B A3B Thinking 2507
- Modality
- text->text
- Tokenizer
- Qwen3
- Instruct type
- —
- Context length
- 131,072
- Max completion
- 32,768
- Prompt $/1M
- $0.130
- Completion $/1M
- $1.560
- 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 | 98 |
| Nebius | 83 |
| AtlasCloudfastest | 83 |
| SiliconFlow | 42 |