# Echo: Cutting Costs to One-Third with Open-Weight Models Fable-level results at one-third the cost. - **Source:** [Hacker News](https://news.ycombinator.com) - **Published:** 2026-07-23 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/b4c0d7ad-9633-4c89-800d-3fc819d80a18 ## What is Echo? Echo is an experiment that uses a pool of open-weight models to create a single AI system. It selects the most suitable models for each task and combines their outputs. ## Initial Experiment The project started with models like GLM-5.2 and Kimi K2.7. Each model was subjected to the same evaluations, and the best combinations were analyzed. ## Hypothesis and Reality The hypothesis was that knowing the best models for each problem in advance would improve performance. Echo aims to achieve this advantage without prior knowledge. ## Computation Allocation Echo decides how much computational power to allocate, which models to use, and how to combine outputs for each request. ## Model Complementarity A model that is generally weaker can be extremely useful in specific problems or combinations. Echo leverages this complementarity. ## Results and Cost Echo achieves results similar to Fable at one-third the cost. However, it can make wrong allocation or combination decisions in some cases. ## Sources covering this story - https://news.ycombinator.com/item?id=49026810 — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._