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

Fireworks vs Nscale

15 vs 24 models, 4 shared

Shared models

ModelFireworks $/1M outFireworks tok/sNscale $/1M outNscale tok/s
Qwen3-8B111 tok/s56 tok/s
Llama-3.3-70B-Instruct109 tok/s16 tok/s
gpt-oss-120b90 tok/s95 tok/s
gpt-oss-20b143 tok/s121 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0