Model Spend Arena2ND ED.
inference-host · 2026-08-14

ShareAI

Official site ↗ · origin not confirmed

inference-host

Serves: open-weight models only (Llama 4, GPT-OSS, Qwen, 150+) on a decentralized GPU grid
Billing unit: tokens
Converts to tokens: full
Verifiable pre-pay: partial
Pricing / discount: 70% of revenue to GPU owners

Not a closed-API reseller but a decentralized inference marketplace: idle GPUs serve open weights, so its prices are real prices for those models. No frontier closed models (no GPT/Claude), so limited for coding against the leaders. Operator HeyShare SRL; country not confirmed.