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

Fireworks vs Together AI

15 vs 29 models, 7 shared

Shared models

ModelFireworks $/1M outFireworks tok/sTogether AI $/1M outTogether AI tok/s
cogito-671b-v2.148 tok/s77 tok/s
DeepSeek-V3.179 tok/s40 tok/s
Llama-3.3-70B-Instruct109 tok/s108 tok/s
Kimi-K2.567 tok/s64 tok/s
gpt-oss-120b90 tok/s81 tok/s
gpt-oss-20b143 tok/s76 tok/s
GLM-570 tok/s42 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0