AI · 2h ago
Echo combines open-weight models to match Fable at one-third cost
Echo is a new AI system that dynamically allocates tasks across a pool of open-weight models, including GLM-5.2 and Kimi K2.7. In evaluations, it matched the performance of the stronger Fable system while using roughly one-third the inference cost. The system is available via a chat interface and an OpenAI-compatible API for testing.
Meridian48 take
The approach is promising, but the real test will be whether Echo's allocation decisions hold up on complex coding and agentic tasks where output quality is harder to measure.
Read the full reporting
Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models →
Hacker News
open-weight-modelsai-orchestration