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

Featherless vs Novita

201 vs 67 models, 12 shared

Shared models

ModelFeatherless $/1M outFeatherless tok/sNovita $/1M outNovita tok/s
Qwen2.5-72B-Instruct14 tok/s
Qwen3-32B15 tok/s
Qwen3.5-397B-A17B47 tok/s
L3-70B-Euryale-v2.135 tok/s
L3-8B-Lunaris-v139 tok/s
L3-8B-Stheno-v3.238 tok/s
WizardLM-2-8x22B10 tok/s
Llama-3.1-8B-Instruct55 tok/s
Meta-Llama-3-70B-Instruct24 tok/s
Meta-Llama-3-8B-Instruct88 tok/s
Kimi-K2-Instruct42 tok/s
GLM-4-32B-041447 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0