Echo routes open-weight models to match Fable at one-third the inference cost
adam_rida · hn · 2026-07-24
Echo is an experiment in treating a pool of open-weight models as one system instead of picking a single model for every task.
- The author evaluated models including GLM-5.2 and Kimi K2.7, then built a router that decides how much compute to spend, which models to call, and how to combine their outputs.
- In early tests, Echo outperformed the best single model in the pool and roughly matched Fable’s aggregate result at about one third of the inference cost.
- The remaining challenge is making better allocation and combination decisions, especially on coding and agentic tasks where quality is harder to measure.
More from Infra
- MiniMax H3 runs fully on a Galaxy S26: 5-second video with audio in ~7 minutes — BidFunny4862 · 2026-10-27
- Unconventional AI acquires inference chip firm NeuReality in 1,000x efficiency bid — NaveenGRao · 2026-10-27
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- RTX 5090 hits $7K as PC gaming community goes into 'denial' over AI boom — PAstynome · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27