Echo: Fable-level Results Using Open-weight Models at a Third of the Cost
Echo delivers Fable-level results using open-weight models while reducing costs.
Echo is an experiment aimed at creating an AI system from multiple open-weight models rather than relying on a single model for every task. It explores how different models can work together to achieve better results for specific problems. In initial evaluations, Echo consistently outperformed the best individual model in its pool and achieved results comparable to Fable at about one-third of the inference cost.