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

Groq vs Novita

6 vs 67 models, 4 shared

Shared models

ModelGroq $/1M outGroq tok/sNovita $/1M outNovita tok/s
Llama-3.3-70B-Instruct252 tok/s34 tok/s
Llama-4-Scout-17B-16E-Instruct374 tok/s63 tok/s
gpt-oss-120b427 tok/s134 tok/s
gpt-oss-20b834 tok/s101 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0