Castform’s RL‑trained open model pulls off 100× cheaper RAG than GPT‑5.6 Sol
Castform uses reinforcement‑learning post‑training on open‑weight models together with Neon’s Lakebase Search, achieving retrieval performance on par with GPT‑5.6 Sol while cutting per‑request cost by a factor of 100 and latency from >10 s to sub‑second. The result shows open models can power affordable, multi‑hop RAG pipelines.