Qwen: Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b
Qwen3.6 35B A3B is a 35B open-weight model (3B active per token), ranking #107 of 235 on the TryAii Score. Its best showing is #17 on Tau2-bench. It's served by 13 independent hosts from $0.1/$0.9 per million input/output tokens — a little under the going rate for its score class.
Prompt $/1M
$0.100
Completion $/1M
$0.900
Context
262,144 tok
Best provider
200 tok/s · WandB
Specs
- Model id
- qwen/qwen3.6-35b-a3b
- Display name
- Qwen: Qwen3.6 35B A3B
- Modality
- text+image+video->text
- Tokenizer
- Qwen
- Instruct type
- —
- Context length
- 262,144
- Max completion
- 235,929
- Prompt $/1M
- $0.100
- Completion $/1M
- $0.900
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- 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 |
|---|---|
| WandB | 200 |
| DekaLLM | 158 |
| Artificial Analysis | 144 |
| AtlasCloudfastest | 135 |
| CoreWeave | 114 |
| Phala | 82 |
| SiliconFlow | 67 |
| Venice | 63 |
| AkashML | 60 |
| DeepInfra | 59 |
| Io Net | 50 |
| Darkbloom | 38 |
| Parasail | 30 |
| Ambient | 21 |
| qwenfastest | — |