{"slug": "show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost", "title": "Show HN: Distill and serve small models with frontier quality for half the cost", "summary": "Experiential Labs launched wmo serve, an open-source tool that routes repetitive agent tasks to distilled smaller models, achieving frontier quality at 40%+ lower cost. The tool uses an OpenAI-compatible endpoint and continuously improves models through distillation from open-source models and token compaction.", "body_md": "Hi HN, we built world-model-optimizer, an open-source tool for continually improve models specialized to agents. Today we are launching `wmo serve`, a tool to route repetitive tasks to distilled smaller models.\n\nAgent traces you already capture are opportunities to get signal on how to make your model cheaper, faster, better. We continuously improve - your specialized model through distillation from open source models - model routing to frontier + custom models - token compaction to remove noise and save tokens\n\nDemo: [https://www.youtube.com/watch?v=2_m4Ze6mdko](https://www.youtube.com/watch?v=2_m4Ze6mdko)\n\nPass in traces and an OpenRouter key, and wmo starts a local OpenAI-compatible endpoint to run with your model at a lower cost with equivalent quality. Behind the scenes a router decides which tasks should go to the frontier versus your model. Tinker continually trains as new traces arrive.\n\nWe also offer a hosted solution for anyone that just wants a frontier quality endpoint with self-improvement over time at a 40%+ lower cost.\n\nSign up for the waitlist at [https://experientiallabs.ai](https://experientiallabs.ai) and give the repo a star!\n\nComments URL: [https://news.ycombinator.com/item?id=49063454](https://news.ycombinator.com/item?id=49063454)\n\nPoints: 3\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost", "canonical_source": "https://github.com/experientiallabs/world-model-optimizer", "published_at": "2026-07-26 23:35:15+00:00", "updated_at": "2026-07-26 23:52:15.252745+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "machine-learning", "developer-tools"], "entities": ["Experiential Labs", "wmo serve", "OpenRouter", "world-model-optimizer"], "alternates": {"html": "https://wpnews.pro/news/show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost", "markdown": "https://wpnews.pro/news/show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost.md", "text": "https://wpnews.pro/news/show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost.txt", "jsonld": "https://wpnews.pro/news/show-hn-distill-and-serve-small-models-with-frontier-quality-for-half-the-cost.jsonld"}}