Io Net pricing overview
TokenWatch tracks 7 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: Mistral Nemo at $0.017 per million input tokens and $0.022 per million output tokens. 7 of 7 text models publish a cache-read price; 7 carry a zero-data-retention tag.
Io Net text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| xiaomi | io-net | Xiaomi: MiMo-V2.6-Flash | $0.100 | $0.280 | $0.0030 | $0.0068 |
| mistral | io-net | Mistral: Mistral Nemo | $0.017 | $0.022 | $0.011 | $0.011 |
| nvidia | io-net | NVIDIA: Nemotron 3.5 Lightning | $0.047 | $0.134 | $0.023 | $0.025 |
| nvidia | io-net | NVIDIA: Nemotron 3.5 Super VL | $0.150 | $0.500 | $0.020 | $0.026 |
| io-net | Google: Gemma 4 26B A4B | $0.090 | $0.310 | $0.041 | $0.044 | |
| io-net | Google: Gemma 4 31B | $0.361 | $1.09 | $0.181 | $0.190 | |
| z-ai | io-net | Z.ai: GLM 5.3 | $0.330 | $3.20 | $0.310 | $0.325 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.