How Zrelay works

From your client to inference

1. Your applicationSend a supported model ID to api.zrelay.net using a Zrelay-issued key and the compatible request format.
2. The Zrelay gatewayZrelay authenticates your key and checks its model family, selected pool and spending allowance.
3. An independent inference supplierThe gateway supplies upstream credentials internally and passes the request to an available route for that model family. Upstream credentials are never distributed to customers.
4. Your response and usageZrelay relays the response, meters reported token usage and settles the cost against your account balance.

Your model choice and selected pool determine the route used for a request. Model availability depends on that pool. The catalog lists the current options; Zrelay does not claim independently verified model provenance.

Supported formats include Claude-compatible Messages, GPT-compatible Responses and Chat Completions, and Grok-compatible Chat Completions. See endpoints and authentication.

Your account, credentials and controls

When an enabled Bitcoin payment settles, Zrelay credits your purchase. Reveal and save your secret account code on the receipt page.

A new Wallet account receives balance without an API key. Sign in with your account code, set up TOTP or a passkey, then create a key for your chosen family and available pool. Legacy purchases may also include an initial API key.

Your account ID is for support. It is separate from your secret account code and cannot be used to sign in.

Paid keys start with zr_live_ and are specific to a model family. Create additional keys, set per-key spending quotas, and revoke or replace keys from the account portal. Your keys share one prepaid balance.

Your prepaid Zrelay balance is an internal service balance used only for API usage. It is not cash, is not transferable between customers, and cannot be withdrawn or redeemed for money. Refunds of eligible purchases follow the Refund Policy and applicable consumer law.

Why it costs less

Zrelay combines demand across customers, shares infrastructure and prepays capacity. Automated metering and lower operating costs also help keep prices competitive.

Zrelay sets its own service rates. Availability and execution depend on capacity and the route used. Zrelay does not claim an official model-provider relationship or an identical backend for every request.

For example, pay $20 and receive $20 of USD API balance. All keys share this balance. Choose Flex for lower rates and variable availability, or Prime for more consistent availability at higher rates. Your selected pool determines the charge at the published Zrelay per-model usage rates.

What your usage report means

Your USD balance reflects confirmed charges and never goes below zero. A request already in progress can finish using the remaining balance; any excess is covered by Zrelay. Input can include system context and cached content reported by the upstream, so billed token counts can differ from the tokens in your visible prompt.

The usage checker shows your balance, confirmed charges and usage by model. Spending quotas apply per key in addition to the shared account balance.

Request data and service dependencies

Requests and responses pass through Zrelay and the upstream inference supplier. Ordinary prompt and output bodies are not kept as conversation history in Zrelay’s application database; bounded upstream error diagnostics may be retained.

Infrastructure and upstream services can also process connection and request data. Read the Privacy Policy and processing provider disclosures.

Models, capacity and routes can become unavailable. Zrelay does not offer a documented uptime SLA. Check service status in the navigation or contact support about a specific problem.