{"type":"post","id":"vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303","slug":"vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303","title":"Vectorize releases Hindsight Models: open-weight decision, rerank and embedding models for agent memory, plus a hosted Inference API","description":"Vectorize released three open-weight models for its Hindsight agent-memory system and a hosted Inference API compatible with Cohere and OpenAI clients.","retrieval_nugget":"Vectorize released three open-weight models for its Hindsight agent-memory system and a hosted Inference API compatible with Cohere and OpenAI clients. The release matters because a small decision model can handle routine judgments inside memory workflows, potentially reducing larger-model calls, cost and latency—but the reported gains come from company-run evaluations.","published_at":"2026-11-03","updated_at":"2026-11-03","record_date":"2026-11-03","date_kind":"published_at","topics":["gemini","agent-memory"],"entities":["Vectorize","Hindsight","hs-decide-1-flash","hs-rerank-1","hs-embed-1","Gemini 3.8 Flash","GLM-5.3-Flash"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Vectorize adds three open-weight agent-memory models, a hosted inference API, and benchmark claims on cost, speed and answer quality; priors cover other embedding/model releases and inference APIs.","prior_refs":["https://newruntime.com/posts/perplexity-releases-pplx-embed-v2-context-open-weight-d1aa40/"],"source_url":"https://hindsight.vectorize.io/blog/2026/11/03/hindsight-models","source_urls":["https://hindsight.vectorize.io/blog/2026/11/03/hindsight-models"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303/","markdown":"https://newruntime.com/posts/vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303.md","json":"https://newruntime.com/posts/vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303.json"},"markdown_url":"https://newruntime.com/posts/vectorize-releases-hindsight-models-open-weight-decision-rerank-d1b303.md","next_reads":[{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.json"},{"type":"topic","path":"/topics/agent-memory/","url":"https://newruntime.com/topics/agent-memory/","title":"Agent Memory","reason":"Explore the agent-memory topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-memory.md","json_url":"https://newruntime.com/topics/agent-memory.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}