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

Hyperbolic vs Novita

13 vs 67 models, 10 shared

Shared models

ModelHyperbolic $/1M outHyperbolic tok/sNovita $/1M outNovita tok/s
Qwen3-235B-A22B-Instruct-250755 tok/s34 tok/s
Qwen3-Coder-480B-A35B-Instruct66 tok/s64 tok/s
Qwen3-Next-80B-A3B-Instruct175 tok/s101 tok/s
Qwen3-Next-80B-A3B-Thinking180 tok/s119 tok/s
DeepSeek-R1117 tok/s40 tok/s
DeepSeek-R1-052896 tok/s38 tok/s
DeepSeek-V3-032441 tok/s32 tok/s
Llama-3.3-70B-Instruct72 tok/s27 tok/s
gpt-oss-120b90 tok/s51 tok/s
gpt-oss-20b95 tok/s97 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0