Qwen
Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b
Input
$0.26
per 1M tokens
Output
$2.08
per 1M tokens
Cached input
—
per 1M tokens
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
- Released
- Context window
- 262K tokens
- Max output
- 66K tokens
- Input
- text, image, video
- Output
- text
- Reasoning
- Yes
Price history
- input $0.40 → $0.26 -35% · output $3.20 → $2.08 -35%
Providers on OpenRouter
4 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| Alibabavendor's own | $0.26 | $2.08 | 262K | 100% | 99.77% |
| SiliconFlowfp8 | $0.26 | $2.08 | 262K | 100% | 97.8% |
| AtlasCloudfp8 | $0.30 | $2.40 | 262K | 100% | 96.5% |
| Novitabf16 | $0.40 | $3.20 | 262K | 81.8% | 99.62% |