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

Novita vs Together AI

67 vs 34 models, 13 shared

Shared models

ModelNovita $/1M outNovita tok/sTogether AI $/1M outTogether AI tok/s
MiniMax-M2.740 tok/s155 tok/s
MiniMax-M339 tok/s19 tok/s
Qwen3-235B-A22B-Instruct-250740 tok/s30 tok/s
Qwen3.5-397B-A17B73 tok/s102 tok/s
DeepSeek-V4-Pro59 tok/s57 tok/s
gemma-4-31B-it20 tok/s72 tok/s
Llama-3.3-70B-Instruct34 tok/s37 tok/s
Kimi-K2.684 tok/s176 tok/s
Kimi-K2.7-Code47 tok/s54 tok/s
gpt-oss-120b134 tok/s107 tok/s
gpt-oss-20b101 tok/s143 tok/s
GLM-535 tok/s107 tok/s
GLM-5.247 tok/s111 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0