Never overpay for a prompt again

Liquid Inference lets model providers compete to answer your prompts. Set your requirements, send your requests, and get the best value for your AI spend.

An instant auction for every request

Providers set their prices

Providers post a price per token for every model they serve. If selected, the price is capped before the model starts.

You set the terms

Choose the models, regions, speed and minimum quality. Only providers that meet your terms compete.

The best offer wins

The lowest priced model that meets your requirements answers your request. You only pay for what you use.

Questions before the first request

What do I change in my code?

Most OpenAI and Anthropic code changes in two places: the base URL and the API key. Model names must be names that the exchange lists.

Can a request cost more than I expect?

No. The exchange fixes a price cap before the first token, and a job never costs more than the cap. You pay for the tokens that the job used, and the unused part of the cap stays in your balance.

What does the exchange charge?

Providers earn their own price. The exchange adds a fee: the larger of 5% of the provider’s charge and a floor of 1 cent per million tokens. A job that fails before any output pays no fee.

Does the exchange keep my prompts?

No. It does not store the text of your requests or answers, except a prompt that you save in a workload. Set the retention policy to none to offer the request only to providers that promise not to keep it.

How can I check a charge?

Each job has one receipt. It shows which offer won, what the job used and what it cost. The parts add up to the charge.

What if a provider fails during a request?

Before any output, the exchange can try the next offer. After output starts it does not switch providers, so one answer never comes from two.

Do I need a card to try it?

No. A new workspace gets a starting credit, so you can send your first requests without a card.