Docs

1. Create a station account or sign in.
2. Open API keys and mint a key. Copy it once.
3. Send the key as Authorization: Bearer rk-….

curl https://relay.169.58.242.32.nip.io/v1/models \
  -H "Authorization: Bearer rk-YOUR_KEY"

curl https://relay.169.58.242.32.nip.io/v1/chat/completions \
  -H "Authorization: Bearer rk-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm/glm-5",
    "messages": [{"role":"user","content":"hello"}]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RELAYSTATION_KEY,
  baseURL: "https://relay.169.58.242.32.nip.io/v1",
});

const reply = await client.chat.completions.create({
  model: "glm/glm-5",
  messages: [{ role: "user", content: "hello" }],
});

Donors start at /contribute, create a login, then an operator grants Contributor on Dashboard → Station users. After that they attach API-key or OAuth accounts (NVIDIA NIM, Claude, Codex, Antigravity, a custom /v1, …). Every connected account fuels the shared station, and each donor gets a personal API key scoped to the accounts they connected. Contributors do not get a private endpoint.

Each account has a plan: monthly tokens, monthly requests, and requests per minute. See plans and your usage page. Model access can be restricted per plan.