Show HN: Liquid Inference – auto-routing to competitive LLM marketplace

Category: ai-ml

Tags: llm, inference, marketplace, routing, cost-optimization

Score: 5.3/10 (Innovation: 6, Technical: 5, Documentation: 2, Utility: 5)

Liquid Inference is a marketplace where LLM providers compete on price for inference, paired with an auto-router that selects the cheapest provider meeting a specified quality level. It applies trading-system principles to LLM inference, letting users customize routing constraints like region and data retention.

Target audience: AI engineers, backend developers, devops

Repository: https://liquidinference.ai/

View on Hacker News