Inference provider
Io Net
4 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
4
Median output speed
113 t/s
Median latency
385ms
Median price / 1M
$0.234
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- V4 Flash 0731DeepSeek51.8
- Qwen3.6 27BQwen37.7
- Qwen3.6 35B A3BQwen32.1
View as table
| Model | Intelligence |
|---|---|
| V4 Flash 0731 (DeepSeek) | 51.8 |
| Qwen3.6 27B (Qwen) | 37.7 |
| Qwen3.6 35B A3B (Qwen) | 32.1 |
Fastest output
Median tokens per second
- Qwen3.6 35B A3BQwen177 t/s
- V4 Flash 0731DeepSeek148 t/s
- Qwen3.6 27BQwen77 t/s
- Mistral NemoMistral AI17 t/s
View as table
| Model | Tokens/s |
|---|---|
| Qwen3.6 35B A3B (Qwen) | 177 |
| V4 Flash 0731 (DeepSeek) | 148 |
| Qwen3.6 27B (Qwen) | 77 |
| Mistral Nemo (Mistral AI) | 17 |
Full catalogue
All 4 models on Io Net
Filter by creator
4 of 4 models| V4 Flash 0731 DeepSeekopen | 51.8 | $0.02 |
| Qwen3.6 27B Qwenopen | 37.7 | $0.32 |
| Qwen3.6 35B A3B Qwenopen | 32.1 | $0.09 |
| Mistral Nemo Mistral AIopen | — | $0.002 |