Qwen3.5 122B A10B
Qwen3.5 122B A10B is Alibaba's language model with a 262K context window and up to 66K output tokens, available from 2 providers, starting at $0.260 / 1M input and $2.08 / 1M output. A native vision-language MoE model with 122B total and 10B active parameters, built on a hybrid linear-attention and sparse MoE architecture for high-efficiency multimodal inference.
Alibaba's language model with a 262K context window and up to 66K output tokens, available from 2 providers, starting at $0.260 / 1M input and $2.08 / 1M output. A native vision-language MoE model with 122B total and 10B active parameters, built on a hybrid linear-attention and sparse MoE architecture for high-efficiency multimodal inference.alibaba-qwen3-5-122b-a10b |
| Language |
| Active |
| Alibaba |
| 262K tokens |
| 66K tokens |
| ImageTextVideo |
| Text |
| default |
| 122B |
| · 2 months ago |
35.9#39 |
31.6#41 |
0.8#28 |
0.1#38 |
0.5#58 |
1.25s#258 |
0.4#95 |
0.6#46 |
0.3#37 |
0.8#37 |
124.5#66 |
Capabilities
Input3/5
✓
✓
·
✓
·
Output1/5
✓
·
·
·
·
Capabilities2/13
✓
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.260 | $2.08 | — | — |
Alibaba Qwen | $0.400 | $3.20 | $0.200 | $1.60 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3.5 122B A10B | 262K | $0.260 | $2.08 | Current | |
| Qwen3.5 35B A3B | 262K | $0.163 | $1.30 | Available | |
| Qwen3.5 397B A17B | 262K | $0.390 | $2.34 | Available |
HuggingFace
519 likes928,022 downloads/month1,469,565 total downloads