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 24 models, 9 shared

Shared models

ModelNovita $/1M outNovita tok/sNscale $/1M outNscale tok/s
Qwen3-235B-A22B11 tok/s22 tok/s
Qwen3-235B-A22B-Instruct-250734 tok/s23 tok/s
Qwen3-32B15 tok/s27 tok/s
DeepSeek-R1-Distill-Llama-70B61 tok/s17 tok/s
Llama-3.1-8B-Instruct55 tok/s59 tok/s
Llama-3.3-70B-Instruct27 tok/s16 tok/s
Llama-4-Scout-17B-16E-Instruct79 tok/s32 tok/s
gpt-oss-120b51 tok/s95 tok/s
gpt-oss-20b97 tok/s121 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0