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

Featherless vs Together AI

207 vs 34 models, 16 shared

Shared models

ModelFeatherless $/1M outFeatherless tok/sTogether AI $/1M outTogether AI tok/s
MiniMax-M2.7155 tok/s
MiniMax-M319 tok/s
Qwen2.5-7B-Instruct123 tok/s
Qwen3.5-397B-A17B102 tok/s
Qwen3.5-9B103 tok/s
DeepSeek-V4-Pro57 tok/s
gemma-4-31B-it72 tok/s
Llama-3.3-70B-Instruct37 tok/s
Meta-Llama-3-8B-Instruct106 tok/s
Kimi-K2.6176 tok/s
Kimi-K2.7-Code54 tok/s
gpt-oss-120b107 tok/s
gpt-oss-20b143 tok/s
GLM-5107 tok/s
GLM-5.154 tok/s
GLM-5.2111 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0