#modelrouting
Live, measured metrics for the hashtag #modelrouting from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #modelrouting
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · fosstodon.org (Mastodon public tags API) · fetched 2026-10-16 03:06 UTC3 uses by 3 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-10-16 03:06 UTCNo related tags with measured usage found for #modelrouting.
Live pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-10-16 03:06 UTCEverything below is measured over the latest 40 public posts (spanning ~2000 hours).
Posting hours (UTC) — busiest: 11:00
Languages: English (40)
Avg boosts / post: 0.1
Top of the latest posts
AssemblyAI (@AssemblyAI) 음성 트랜스크립션 작업에서 항상 프런티어 모델을 쓸 필요는 없다는 비용·품질 분석이다. 15분 이하 오디오에서는 최고 점수 모델과 품질 차이가 2점 이내인 대안 모델이 시간당 비용을 50~85배 낮출 수 있으며, 1시간짜리 긴 트랜스크립트에서는 비용 격차가 약 3배로 줄어든다. 작업 길이별 모델 라우팅·비용 최적화에 참고할 만하다. https://x.com/AssemblyAI/sta
Min Choi (@minchoi) 업무 유형별 LLM 사용 워크플로를 제안했다. 실시간 리서치·계획과 업무 보조에는 Grok Bot, 아키텍처 설계·복잡한 코딩·프론트엔드/디자인에는 Opus 5.5, 일상적인 코딩·디버깅과 테스트 작성·실행에는 Sonnet 5.5를 배치하는 방식이다. 모델별 강점을 기준으로 작업을 라우팅하는 실무적 참고 사례다. https://x.com/minchoi/status/210930033720318
Anthropic's advisor tool pairs Opus as planner with Haiku as executor. Build the orchestrator-worker cost stack that cuts agent spend.#aiagents #costoptimization #claude #modelrouting #software #coding #development #engineering #inclusive #
#modelrouting across platforms
every network with a public tag surfaceFollow #modelrouting straight to each platform’s own tag page. Where a platform publishes open data we measure it above; the rest lock their numbers behind paid APIs, so we link rather than guess.
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/modelrouting