Host Io Net raised Qwen3.6 35B A3B input pricing by 43%
Published 18 September 2026
Price move, per 1M tokens
- Io Net · input↑ 43%$0.133 → $0.190
- Io Net · output↑ 5%$0.94 → $0.99
- Io Net · cache read↑ 49%$0.0665 → $0.0990
| host | rate | was | now | change |
|---|---|---|---|---|
| Io Net | input | $0.133 | $0.190 | ↑ 43% |
| Io Net | output | $0.94 | $0.99 | ↑ 5% |
| Io Net | cache read | $0.0665 | $0.0990 | ↑ 49% |
input: ↑ 43%
If you buy
budget for a higher input and cache-read cost on this host, so re-check your prompt sizes and cache hit rate before your next top-up.
The model
Qwen3.6 35B A3Bopen the model →
Open weights36B parameters262K context12 hosts
No leaderboard with a large enough field rates this model yet.
Qwen 3.6 is a multimodal model with a mixture-of-experts design that keeps only 3 billion parameters active for each word while drawing on 36 billion total. It carries a permissive Apache licence and is widely available from thirteen hosts, though no benchmark scores have been published yet.
Source
Read on openrouter.ai · we published this on 18 September 2026.
read the original at openrouter.ai ↗