{"id":"billion-scale-vector","slug":"billion-scale-vector","name":"Billion-scale vector search","shortName":"Billion-scale vector search","problemStatement":"ANN at enormous scale with serious indexing.","whenNotTopPick":"Under ~50–100M vectors — don't pay the complexity tax.","categoryIds":["cat-vector-memory"],"depotPickProviderId":"zilliz","depotPickRationale":"capability scale + maturity.","runnersUpIds":["qdrant","pinecone","turbopuffer"],"weights":{"capabilityFit":0.24,"pricePerformance":0.18,"latencyReliability":0.18,"developerDx":0.16,"privacyPosture":0.1,"lockInRisk":0.08,"maturity":0.06},"methodologyNotes":"capability scale + maturity.","tags":["billion"],"depth":{"whenNotToUse":{"text":"Under ~50–100M vectors — don't pay the complexity tax.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"qdrant","name":"Qdrant","overallForJob":8.57,"pickOverallForJob":8.1,"beatsPickOn":["pricePerformance","latencyReliability","developerDx","privacyPosture","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":3.5,"runnerUpLockInRisk":3,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["open source (provider tag `oss`)"],"runnerUpExitSignals":["open source (provider tag `oss`)"],"pickNotes":[{"text":"Open-source Milvus core","field":"strengths"}],"selfHostFallback":[{"id":"milvus","name":"Milvus","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/milvus-io/milvus/master/LICENSE"}],"migration":"Runner-up Qdrant has lower stored lock-in risk (3 vs 3.5, 0–10, higher = more lock-in). Pick exit signals: open source (provider tag `oss`). Self-host fallback listed for this job: Milvus.","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":1,"pricingRows":0,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}},"depotPick":{"id":"zilliz","slug":"zilliz","name":"Zilliz (Milvus)","tagline":"When you're truly at massive scale, Milvus/Zilliz earns its complexity. Don't start here for a chatbot MVP.","overall":8.1},"runnersUp":[{"id":"qdrant","slug":"qdrant","name":"Qdrant","tagline":"Depot pick for serious vector workloads with filters. Self-host or Cloud — either way you can leave.","overall":8.57},{"id":"pinecone","slug":"pinecone","name":"Pinecone","tagline":"Still the zero-ops vector default. If you already run Postgres, try pgvector before paying Pinecone rents.","overall":7.88},{"id":"turbopuffer","slug":"turbopuffer","name":"Turbopuffer","tagline":"When your vector bill scares you and much of the corpus is cold, Turbopuffer is the interesting answer.","overall":8.23}]}