vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

Novita vs Z.ai

67 vs 15 models, 8 shared

Shared models

ModelNovita $/1M outNovita tok/sZ.ai $/1M outZ.ai tok/s
GLM-4.555 tok/s53 tok/s
GLM-4.5-Air74 tok/s69 tok/s
GLM-4.5V51 tok/s47 tok/s
GLM-4.6100 tok/s87 tok/s
GLM-4.6V-Flash38 tok/s48 tok/s
GLM-4.794 tok/s86 tok/s
GLM-4.7-Flash24 tok/s50 tok/s
GLM-539 tok/s38 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0