Architect launches Liquid Inference, a router where providers bid for lowest-cost tokens
IanAndrewsDC · x · 2026-10-08
Architect (founded by Brett Harrison) launched Liquid Inference, an LLM router where inference providers dynamically compete to offer the lowest-cost tokens. Providers onboard in minutes, buyers get full price visibility plus 20% of referred fees back as free inference, and the team applies financial-exchange experience to real-time two-sided price discovery. It's OpenAI/Anthropic API-compatible and works as a drop-in backend for Claude Code, Codex, Cursor, Cline and more.
Related event: Architect Launches Liquid Inference with Real-Time Bidding(3 posts)→
More from Venture
- "Journalists shouldn't report ARR numbers — it's a fake science," and an AI professor agrees — DavidSKrueger · 2026-10-09
- Catalyst launches autonomous AI trading agent backed by Jake Paul — jzlegion · 2026-10-09
- When compute debt outpaces user cash: margins flow from software to physical asset owners — LexSokolin · 2026-10-09
- NeurIPS Paper Releases Market-1T, a ~1 Trillion-Observation Financial Dataset — randall_balestr · 2026-10-09
- Contra's Creative Intelligence 2026 report: AI-powered creative project sizes jump 40%+ — heyshrutimishra · 2026-10-09
- LMArena Scales From 5 to 20 as It Continues a16z Partnership — arena · 2026-10-09