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

Fireworks vs OVHcloud

15 vs 7 models, 3 shared

Shared models

ModelFireworks $/1M outFireworks tok/sOVHcloud $/1M outOVHcloud tok/s
Llama-3.3-70B-Instruct109 tok/s30 tok/s
gpt-oss-120b90 tok/s131 tok/s
gpt-oss-20b143 tok/s85 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0