Architect launches Liquid Inference, a per-request auction router for LLM inference

Architect Financial Technologies has launched Liquid Inference, an LLM router that auctions each request to providers quoting the requested model, with the lowest qualifying offer winning.

Buyers can set per-job cost caps, time-to-first-token limits, minimum throughput, and region or zero-data-retention rules, and the maximum price is locked before generation begins.

According to the MarkTechPost report, signup is free and the first 500 users receive $20 of free inference, a figure the report attributes to Harrison. The source states that fees, the provider list, and latency data are not yet public, so the router's actual pricing and performance cannot yet be assessed.