Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models
474 points by adam_rida 48 days ago | 222 comments
tl;dr: Echo is a routing system that dynamically allocates queries across a pool of open-weight models (GLM-5.2, Kimi K2.7, etc.), deciding per-request which models participate and how their outputs combine. The author claims it outperforms any single model in the pool and matches Fable's aggregate performance at roughly one-third the inference cost. A chat UI and OpenAI-compatible API are available for testing, with coding/agentic task evaluation still underway.
HN Discussion:
  • Dark patterns and premature launch (fake input box, forced signup, no trial) drive users away
  • Lack of transparency: no benchmarks, no listed models, AI-generated marketing content undermines credibility
  • Cost savings are unappealing given heavily subsidized incumbent plans exist
  • Routing/orchestration across models is a promising architectural direction for the future
  • The approach is derivative or technically flawed (breaks caching, resembles old meta-search or existing OpenRouter Fusion)