KT

Inference host · 4 models · 4 priced routes

Models on KT

Model	In / out per 1M	Vs headline
Gemma 4 31B Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.	$0.1 / $0.34Same vs headline	Same	Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
GLM 5.3 Flash GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.15 / $0.5+389% vs headline	+389%	GLM-5.3-Flash is a native multimodal model from Z.ai.
Nemotron 3 Ultra NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).	$0.5 / $2.2+25% vs headline	+25%	NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
Kimi K3 Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.	$3 / $15Same vs headline	Same	Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.