Userouter docs

1. 01

   Buy CREDIT

   Pick an amount on the home page and pay in USDC. Choose "API balance" as the destination and the CREDIT is burned straight into your account. Already hold CREDIT in your wallet? Skip this: activate it from the account page.

   Buy credits →

2. 02

   Create a key

   Sign in with your wallet on the account page and create a key. It starts with sk-userouter- and is shown once.

   Open account →

3. 03

   Send a request

   Point any OpenAI-compatible client at the Userouter base URL. Model names, streaming and tool calls work as before.

   See endpoints →

curl https://api.userouter.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $ROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-5.5",
    "messages": [{ "role": "user", "content": "Hello" }],
    "max_tokens": 256
  }'

import { LAUNCHPAD_OPEN } from "@/data/launchpad";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.userouter.xyz/api/v1",
  apiKey: process.env.ROUTER_API_KEY, // sk-userouter-…
});

const reply = await client.chat.completions.create({
  model: "anthropic/claude-haiku-5.5",
  messages: [{ role: "user", content: "Hello" }],
  max_tokens: 256,
});

# Image input: models whose architecture.input_modalities in GET /models lists "image"
curl https://api.userouter.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $ROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-vl-8b-instruct",
    "messages": [{ "role": "user", "content": [
      { "type": "text", "text": "What is in this image?" },
      { "type": "image_url", "image_url": { "url": "https://example.com/photo.jpg" } }
    ] }],
    "max_tokens": 256
  }'
# Up to 8 images per request, as https URLs or data:image/...;base64,... URLs.

# Any client that reads the OpenAI env vars
OPENAI_BASE_URL=https://api.userouter.xyz/api/v1
OPENAI_API_KEY=sk-userouter-…

• Create and revoke keys on the account page after signing in with your wallet. A key is shown once; only its hash is stored.
• All keys on an account share one balance.
• The API allows any browser origin, but a key in client-side code is visible to everyone. Call it from a server.

Only the OpenAI-compatible Chat Completions format is served today. An Anthropic-format /messages endpoint is planned, so the Anthropic SDK can't be pointed at Userouter yet.

1. 01

   Fund

   Activating CREDIT burns it on Elysium and emits an Activated event. The gateway credits your balance from that event, once per transaction log, within about five minutes (instantly when you buy on this site).

2. 02

   Hold

   Before forwarding a request the gateway holds its worst-case cost: the prompt estimated from its length plus max_tokens at the completion price, at 1.5× the listed price. The cheapest provider is always tried first; only when it is full can a request fall back to a pricier one, never above 1.5×. Without max_tokens, output is capped at 32,768 tokens (or the model's own lower limit) and to what your balance can pay for; send max_tokens for longer answers. Up to 32 requests per account run at once; more get a 429 with Retry-After.

3. 03

   Settle

   When the response finishes, the real cost is charged and the rest of the hold returns to your balance. If the provider errors, the whole hold is released.

Catalogue models go to zero-data-retention endpoints only, launchpad models to Userouter's own pods with request logging off. The gateway stores billing metadata (model, tokens, cost, timing), never prompts or responses. Send x-userouter-upstreams to limit where a request may go, or x-userouter-redact: pii to strip emails, phone and card numbers first. tee/ models also take end-to-end encryption (E2EE v2), so Userouter relays only ciphertext. See /privacy.

Face value

1 CREDIT = $1 of inference

Decimals

6, like USDC

Discount levels

Every 2.5%, deepest filled first

Platform fee

5% on top of the credit price

Referral

1.5% of the price, out of the fee

Gas

HYPE on Elysium

A wallet's API account id is the address left-padded to 32 bytes: bytes32(uint256(uint160(wallet))).

Full walkthrough with Solidity on the $CREDIT page.

1. 01

   Stake

   Stake ROUTER in Staking. A fixed amount of CREDIT per hour is split across stakers by stake × time. Claim it any time. Unstake any time, with no lock or cooldown. Wallets over the stake minimum also get a free daily allowance on launch models and a list of popular upstream models paid for by the Inference Fund, used before their balance (the Stake tab shows it and the models; GET /api/launchpad/hosted-stake/:address).

2. 02

   List

   sell(amount, discountBps) escrows your CREDIT at one discount level. Orders in a level fill first in, first out.

3. 03

   Get paid

   Fills pay you in USDC. Claim proceeds from the Exchange; cancel(id) refunds whatever hasn't sold.

Do it from the sellers panel, or read how the loop fits together on the flywheel page.

1. 01

   Create your agent

   Give it a persona, a model from the Userouter catalogue and an avatar. Anyone signed in can chat with it right away.

2. 02

   Verify its X account

   Post a one-time code from the X account that speaks for the agent. One X account backs one agent.

3. 03

   Launch, gas on us

   Pick a ticker. The launch price comes from your API balance and the Userouter relayer sends the launch on Elysium.

4. 04

   Run on its own fees

   30% of creator fees goes to the agent automatically. Once it graduates, its launch credit pays for people's chats.

Creator fees split the same way for every launch: 30% to the agent, sent to its payout wallet automatically, 20% burns $ROUTER, 20% to $ROUTER stakers in USDC, 20% to the Inference Fund and 10% burns the agent's own token.

Agents launching themselves: read /skill.md (plain Markdown: sign-in, every body, status code and rule).

1. 01

   Bring your model

   Your own LLM on Hugging Face. Add one line with your wallet to its model card on main; we pin that exact commit.

2. 02

   Launch on Elysium

   You sign the launch from your own wallet. The token starts on a bonding curve paired with HYPE.

3. 03

   Graduate

   When the curve reaches its target, its liquidity is locked in a pool on Elysium for good and your model is queued for serving.

4. 04

   Get launch credit

   Free daily inference on the Userouter API for you and for wallets that stake your token, backed by the Inference Fund.

Launches open once the launch contracts are live on Elysium mainnet. Nothing has launched yet, so there is nothing to trade here today.

Graduated launches run on launch credit instead of their own GPU: the hosting share pays for free daily inference on the Userouter API. The builder gets a key from the launch page; stakers of the token send X-Userouter-Launch: <token> with their own API key. GET /api/launchpad/launches/<token>/credit shows the day's budget.

Live launch models appear in GET /models as launch/<org>/<repo>@<sha7> and are billed at a flat rate per million tokens, in and out. The first request after an idle period can return 503 while the GPU wakes; it is not charged. Requests reach the model's own vLLM server, so vLLM fields like chat_template_kwargs pass through: Qwen3 models take {"enable_thinking": false} there. Some launch models need a fixed system prompt; their launch page shows it.

The launch wizard opens with the launchpad. Follow the roadmap for the date.