Architect Launches Liquid Inference with Real-Time Bidding

Architect launched Liquid Inference, an OpenAI/Anthropic-compatible routing service aggregating 700+ models from multiple inference providers that bid in real time per prompt to deliver the lowest token prices.

2026-10-08 ~ 2026-10-09 · 3 related posts

• Liquid Inference launches aggregator routing across six inference providers — markjeffrey · 2026-10-08
• Architect launches Liquid Inference, a router where providers bid for lowest-cost tokens — IanAndrewsDC · 2026-10-08
• Architect Fi launches Liquid Inference, a router where providers bid per-prompt across 700+ models — markjeffrey · 2026-10-09