Reduce token cost with Metrum AI Router – routing intelligence you can train
Metrum AI Router Agent workloads often make dozens of model calls per task. Paying frontier price for each call is the default path, and token spend shows up after the monthly budget is gone. In one committed Harbor run, Codex on big-coder used 48,470 Harbor input tokens in a single deterministic job (docs/harbor-case-study.md).
- ▪Metrum AI Router Agent workloads often make dozens of model calls per task.
- ▪Paying frontier price for each call is the default path, and token spend shows up after the monthly budget is gone.
- ▪In one committed Harbor run, Codex on big-coder used 48,470 Harbor input tokens in a single deterministic job (docs/harbor-case-study.md).
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,603 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/metrum-ai/router |
| Publication time | Sat, 12 Sep 2026 14:39:20 +0000 |
| Retrieval time | 2026-09-12T16:45:11.138Z |
| Last seen | 2026-09-12T16:45:26.613Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | nXTnkYbzRMNL · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Metrum AI Router Agent workloads often make dozens of model calls per task. Paying frontier price for each call is the default path, and token spend shows up after the monthly budget is gone. In one committed Harbor run, Codex on big-coder used 48,470 Harbor input tokens in a single deterministic job (docs/harbor-case-study.md). A model group is a quality and cost contract you define. Routing picks the cheapest eligible candidate with evidence of meeting that contract. Evidence expires through the group contract field max_eval_age_days, so stale validation drops targets from eligibility. Learned Routing Policy abstains when uncertainty is high. Token budgets and quotas are admitted before any cache-miss upstream call. See Model Group Contracts and docs/MODEL_GROUP_CONTRACTS.md.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.