OffPeak

Open-model inference priced by live GPU availability. Built on Robinhood Chain.
TG:

[OffPeak @UseOffPeak]

Introducing Offpeak ($OFPK): a market for real GPU capacity.

Run open-model inference through an OpenAI-compatible API, schedule flexible jobs for lower-cost hours, or reserve capacity.

Pay by key or x402. Withdraw unused USDG. Verify every request with signed usage records.

A full @RobinhoodApp build…

[OffPeak @UseOffPeak]

A wallet approval should have a ceiling. OffPeak's proposed P0 flow uses capped quotes so a buyer sees the maximum authorized amount before approving a request. A cap can control spend; it cannot guarantee the model will meet your quality bar.

[OffPeak @UseOffPeak]

Prompt privacy has a specific boundary in the current design: transient processing without prompt logging is proposed, while encrypted response artifacts may be retained for up to 24 hours and billing metadata for 90 days. That is not zero retention.

[OffPeak @UseOffPeak]

Think of OffPeak as a proposal for buying one AI task from a vetted compute operator. You would see a capped quote, approve it with a wallet, then receive the response and a signed usage record. A live service has not been demonstrated.

[OffPeak @UseOffPeak]

A signed receipt could show what usage a request reported and how billing was calculated. It cannot grade the answer. If an output is poor, a payment record alone will not tell you why.

[OffPeak @UseOffPeak]

OffPeak starts with a narrow buyer: a developer with repeatable text work, a model that meets their quality bar, and some flexibility about when spare capacity is available. The proposed service aims to make the request and its price easier to review before a wallet approves it. Hosts are not confirmed live.

[OffPeak @UseOffPeak]

Changing model versions can change outputs even when the prompt stays the same. OffPeak's P0 plan starts with one approved model, so a quote can say what it covers. That is a scope choice, not a claim about model quality.

[OffPeak @UseOffPeak]

https://t.co/vfdU29boSL

[OffPeak @UseOffPeak]

A low inference price only helps when a buyer can compare it with a real service. A quote should name the model, workload, capacity window, and interruption rules it covers. OffPeak’s materials frame this as a design question; they do not confirm live supply.

[OffPeak @UseOffPeak]

A quote should tell you more than the hourly rate. It should name the model or service class, the work it covers, how long the offer holds, and whether your request is reserved or simply competing for spare capacity. Those details make two prices comparable.

[OffPeak @UseOffPeak]

OffPeak’s documents propose matching inference demand with spare GPU supply. The market becomes useful when price, capacity, timing, interruption, and billing terms are visible together.

[OffPeak @UseOffPeak]

A GPU reservation is useful only if both sides know what was reserved. “Capacity” needs a model, a workload, a quantity, and a time window.

[OffPeak @UseOffPeak]

A public hourly total can support reconciliation. It should not require publishing private prompt content to make the accounting checkable.

[OffPeak @UseOffPeak]

OffPeak is built around a simple idea: spare GPU capacity can serve useful AI work when buyers can see the terms. A request should make its model, workload, budget, and time window clear before a provider accepts it. The project documents describe this design; live capacity is not confirmed.