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

OVHcloud vs Together AI

8 vs 34 models, 5 shared

Shared models

ModelOVHcloud $/1M outOVHcloud tok/sTogether AI $/1M outTogether AI tok/s
Qwen3.5-397B-A17B86 tok/s102 tok/s
Qwen3.5-9B40 tok/s103 tok/s
Llama-3.3-70B-Instruct27 tok/s37 tok/s
gpt-oss-120b92 tok/s107 tok/s
gpt-oss-20b74 tok/s143 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0