Qwen
Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b
Input
$0.14
per 1M tokens
Output
$1.00
per 1M tokens
Cached input
$0.05
per 1M tokens
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
- Released
- Context window
- 262K tokens
- Max output
- 82K tokens
- Input
- text, image, video
- Output
- text
- Reasoning
- Yes
Price history
No price changes since we started tracking on .
Providers on OpenRouter
7 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 |
|---|---|---|---|---|---|
| Darkbloomfp4 | $0.065 | $0.75 | 262K | 100% | 100% |
| DeepInfrafp8 | $0.14 | $1.00 | 262K | 100% | 99.02% |
| Parasailfp8 | $0.15 | $1.00 | 262K | 100% | 99.84% |
| Venice | $0.15 | $1.00 | 256K | 100% | 99.78% |
| Alibabavendor's own | $0.163 | $1.30 | 262K | 100% | 100% |
| AtlasCloudfp8 | $0.225 | $1.80 | 262K | — | 98.7% |
| SiliconFlowfp8 | $0.24 | $1.80 | 262K | — | 81.8% |