Inference provider
Io Net
6 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
6
Median output speed
117 t/s
Median latency
265ms
Median price / 1M
$0.159
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
- GLM 5.3Z.ai44.8
- MiMo-V2.6-FlashXiaomi37.9
- Nemotron 3.5 LightningNVIDIA12.9
View as table
| Model | Intelligence |
|---|---|
| GLM 5.3 (Z.ai) | 44.8 |
| MiMo-V2.6-Flash (Xiaomi) | 37.9 |
| Nemotron 3.5 Lightning (NVIDIA) | 12.9 |
Fastest output
Median tokens per second
- Nemotron 3.5 LightningNVIDIA226 t/s
- Gemma 4 31BGoogle193 t/s
- GLM 5.3Z.ai138 t/s
- Mistral NemoMistral AI96 t/s
- Gemma 4 26B A4B Google95 t/s
- MiMo-V2.6-FlashXiaomi82 t/s
View as table
| Model | Tokens/s |
|---|---|
| Nemotron 3.5 Lightning (NVIDIA) | 226 |
| Gemma 4 31B (Google) | 193 |
| GLM 5.3 (Z.ai) | 138 |
| Mistral Nemo (Mistral AI) | 96 |
| Gemma 4 26B A4B (Google) | 95 |
| MiMo-V2.6-Flash (Xiaomi) | 82 |
Full catalogue
All 6 models on Io Net
Filter by creator
6 of 6 models| GLM 5.3 Z.aiopen | 44.8 | $0.39 |
| MiMo-V2.6-Flash Xiaomiopen | 37.9 | $0.03 |
| Nemotron 3.5 Lightning NVIDIAopen | 12.9 | $0.02 |
| Gemma 4 26B A4B Googleopen | — | $0.03 |
| Gemma 4 31B Googleopen | — | $0.04 |
| Mistral Nemo Mistral AIopen | — | $0.002 |