Io Net

Inference host · 6 models · 6 priced routes

Models on Io Net

Model	In / out per 1M	Vs headline
Mistral Nemo fp16 · A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.	$0.023 / $0.03+18% vs headline	+18%	fp16 · A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.
Nemotron 3.5 Lightning NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.	$0.07 / $0.2+110% vs headline	+110%	NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
Gemma 4 26B A4B bf16 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.	$0.09 / $0.31+71% vs headline	+71%	bf16 · Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Nemotron 3.5 Super VL nvfp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.	$0.15 / $0.5+79% vs headline	+79%	nvfp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Gemma 4 31B Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.	$0.38 / $1.15+258% vs headline	+258%	Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Kimi K3 fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$1.5 / $14-23% vs headline	-23%	fp4 · Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.