Trading Firm Auctions Every LLM Call

🔥 What happened Architect Financial Technologies — the firm behind the AX perpetual futures exchange — launched Liquid Inference, a router that runs a live auction on every LLM request. Providers bid per prompt; the cheapest offer meeting the buyer's rules wins. Migration is a base-URL swap, no code changes. 💡 Why it matters Buyers set cost caps, time-to-first-token limits and zero-data-retention rules, with the max price locked before the first token. Unlike OpenRouter's price-weighted balancing, this is genuine two-sided price discovery with a public order book. First 500 users get $20 in free inference. ⚡ Our take A trading desk is rebuilding the compute market before the AI labs do. Once GPUs become a tradable commodity, the best spread beats the best model.