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

Novita vs Nscale

67 vs 19 models, 6 shared

Shared models

ModelNovita $/1M outNovita tok/sNscale $/1M outNscale tok/s
Qwen3-235B-A22B16 tok/s14 tok/s
Qwen3-235B-A22B-Instruct-250740 tok/s13 tok/s
Llama-3.1-8B-Instruct163 tok/s143 tok/s
Llama-4-Scout-17B-16E-Instruct63 tok/s65 tok/s
gpt-oss-120b134 tok/s115 tok/s
gpt-oss-20b101 tok/s155 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0