Qwen: Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b
Qwen3.5-122B-A10B is an open-weight heavyweight from Qwen — 122B parameters with 10B active per token, ranking #108 of 261 on the TryAii Score. Its best showing is #17 on IFBench. API pricing starts at $0.26/$2.08 per million input/output tokens, though similar scores now sell for about $1.5 per million output tokens, with 3 independent hosts serving it. It's reasonably quick at roughly 49-98 tokens/sec.
Prompt $/1M
$0.260
Completion $/1M
$2.080
Context
262,144 tok
Best provider
133 tok/s · Artificial Analysis
Specs
- Model id
- qwen/qwen3.5-122b-a10b
- Display name
- Qwen: Qwen3.5-122B-A10B
- Modality
- text+image+video->text
- Tokenizer
- Qwen3
- Instruct type
- —
- Context length
- 262,144
- Max completion
- 65,536
- Prompt $/1M
- $0.260
- Completion $/1M
- $2.080
- 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 |
|---|---|
| Artificial Analysis | 133 |
| Alibabafastest | 98 |
| AtlasCloud | 64 |
| Novita | 49 |
| SiliconFlow | 47 |