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

Fireworks vs Novita

13 vs 67 models, 10 shared

Shared models

ModelFireworks $/1M outFireworks tok/sNovita $/1M outNovita tok/s
MiniMax-M2.7166 tok/s40 tok/s
MiniMax-M395 tok/s39 tok/s
DeepSeek-V4-Flash59 tok/s86 tok/s
DeepSeek-V4-Pro47 tok/s59 tok/s
Kimi-K2.579 tok/s57 tok/s
Kimi-K2.692 tok/s84 tok/s
Kimi-K2.7-Code120 tok/s47 tok/s
gpt-oss-120b182 tok/s134 tok/s
gpt-oss-20b83 tok/s101 tok/s
GLM-5.251 tok/s47 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0