OpenAlchemyOpenAlchemy
100% 社区 GPU 网络 · 上线中

别再为 AI 付费了。
把您的 GPU 接上来。

Grid 把您闲置的 GPU 时间,变成模型 API 的点数。

机器有空时,分享出去。
需要推论时,使用网络。

免费跑模型,或把收益兑现。

加入 Grid
免费使用
GPU 服务请求时累积点数 · 用于自己的推论
不加入的话
依代币计费
低于市场 · 美元 · 免信用卡起步
提供者分润
70%
每一笔兑现的点数 · 每月支付
模型
开源
Qwen · Llama · Mistral · DeepSeek · Flux · Whisper · Kokoro

Anywhere a host joins.

We don't own GPUs and we don't run a data center. Every node on the map is contributed by someone. Tokyo is where the project started — the rest grows wherever a host plugs in.

livepotential

Models available

Open-source weights, served on the network. Pricing in USD, per-token where applicable.

ModelTypePriceStatus
qwen3.5-72b-instruct
chat$0.30/1Klive
llama-4-70b-instruct
chat$0.28/1Klive
gemma-3-27b-it
chat$0.18/1Klive
deepseek-v4
chat$1.10/1Ksoon
qwen3.5-vl-72b
vision$0.40/1Klive
pixtral-12b
vision$0.15/1Klive
whisper-large-v3
audio$0.04/minlive
kokoro-tts-v1
tts$0.08/1Klive
flux-schnell
image$0.50/imglive
bge-reranker-v2-m3
rerank$0.02/1Klive
For GPU owners

Got a spare GPU? Join Grid. Use the network for free.

Install OpenAlchemy Engine on any GPU you have — from 8 GB to 80 GB. Grid matches your VRAM to the right models: small GPUs run embeddings and small chat, large GPUs run 70B+. Earn credits as the network uses your GPU. Spend them on your own inference for free, or cash out at 70% revenue share. No contracts.

1
Install
Download Engine (Windows now, macOS / Linux soon). 60-second install.
2
Pair
Paste a one-time code from your dashboard. We auto-detect GPUs.
3
Earn
Credits land as requests are served. Use them for free inference or cash out at 70%.