io.net: Models and Prices
Decentralized GPU network with an inference API.
io.net served 99B tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #39 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Flash | MiMo | 0.5% | 55B | $0.26 | $0.41 | 47 | 99.7% | 1.05M |
| Gemma 4 26B A4B | Gemma | 8.1% | 21B | $0.048 | $0.21 | 56 | 100.0% | 262K |
| Nemotron 3.5 Lightning | Nemotron | 1.3% | 11B | $0.047 | $0.134 | 110 | 100.0% | 262K |
| Mistral Nemo | Mistral | 3.1% | 8B | $0.018 | $0.024 | 43 | 100.0% | 128K |
| GLM 5.3 | GLM | <0.1% | 1B | $0.75 | $3.40 | 71 | 97.5% | 262K |
| Gemma 4 31B | Gemma | 0.2% | 1B | $0.361 | $1.09 | 38 | 95.5% | 262K |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- io.net
- Headquarters
- United States
- Status page
- status.io.net
Sources: io.net.
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com