# Faiss vs Turbopuffer

**Leader by Vioscale score:** Turbopuffer

| Attribute | Faiss | Turbopuffer |
|---|---|---|
| **Vioscale score** | 62 (36% (low)) | 70 (61% (medium)) |
| activity.commits_last_30d | 47 | - |
| adoption.dependent_repos | 5,592 | - |
| adoption.github_stars | 40,809 | - |
| deployment.options | `{"self_hosted":true}` | `{"cloud":true,"hybrid":true,"on_prem":true,"self_hosted":true}` |
| description.long | Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. | Vector and full-text search database built on object storage, offering 10x cheaper cost and extreme scalability for AI applications, semantic search, and recommendation systems. |
| features.capabilities | `{"ann_index":"HNSW, IVF, PQ, multi-index, NSG","deployment":"self_hosted","serverless":false,"quantization":"product","storage_tier":"disk_backed","licence_class":"permissive_oss","product_class":"extension","distance_metrics":"Euclidean (L2), inner product, L1, Linf","horizontal_scale":"single_node"}` | `{"deployment":"managed","serverless":true,"consistency":"tunable","storage_tier":"tiered","hybrid_search":true,"licence_class":"proprietary","multi_tenancy":true,"product_class":"dedicated_dbms","full_text_bm25":true,"horizontal_scale":"sharded_distributed","metadata_filtering":"pre_filter"}` |
| language.primary | C++ | - |
| license.spdx | MIT | - |
| market.availability | - | `{"hqCountry":"CA","primaryMarkets":["US","CA"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"mac":true,"linux":true,"windows":true}` | `{"web":true}` |
| pricing | `{"type":"open_source","sourceUrl":"https://faiss.ai","retrievedAt":"2026-08-13T20:46:34.341Z"}` | `{"type":"usage","plans":[{"free":false,"name":"Launch","summary":"$16/month minimum, usage-based overage","commitment":"monthly","components":[{"kind":"fixed","amount":16,"period":"month","currency":"USD"}],"description":"Entry-level plan with usage-based billing","contactSales":false},{"free":false,"name":"Scale","features":["IP allowlisting","SSO"],"description":"Mid-tier plan with advanced security features","contactSales":false},{"free":false,"name":"Enterprise","features":["Customer managed encryption","Private networking","IP allowlisting","SSO","Privileged access management","Single-tenancy clusters","BYOC"],"description":"Custom enterprise deployment with advanced security and compliance","contactSales":true}],"addOns":[{"name":"Namespace pinning"}],"summary":"From $16/month. Usage-based with per-TB-queried pricing ($1/PB base rate with volume discounts up to 96%).","currency":"USD","freeTier":false,"sourceUrl":"https://turbopuffer.com/docs/pricing-log","retrievedAt":"2026-08-13T20:43:39.812Z","startingPrice":{"amount":16,"period":"month","currency":"USD"},"billingPeriods":["month"]}` |
| pricing.free_tier | - | no |
| pricing.model | commercial | commercial |
| pricing.price_level | free | mid |
| pricing.transparent | - | yes |
| release.cadence_days | 83 | - |
| release.history | `[{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.15.0","date":"2026-08-03T17:10:58Z","type":"stable","version":"v1.15.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.14.3","date":"2026-06-13T04:03:53Z","type":"stable","version":"v1.14.3"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.14.2","date":"2026-05-22T20:05:00Z","type":"stable","version":"v1.14.2"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.14.1","date":"2026-03-06T17:49:04Z","type":"stable","version":"v1.14.1"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.14.0","date":"2026-03-03T03:19:33Z","type":"stable","version":"v1.14.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.13.2","date":"2025-12-19T23:41:59Z","type":"stable","version":"v1.13.2"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.13.1","date":"2025-12-03T00:02:15Z","type":"stable","version":"v1.13.1"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.13.0","date":"2025-11-12T17:18:44Z","type":"stable","version":"v1.13.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.12.0","date":"2025-08-12T16:46:55Z","type":"stable","version":"v1.12.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.11.0","date":"2025-04-25T14:13:55Z","type":"stable","version":"v1.11.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.10.0","date":"2025-01-31T23:29:10Z","type":"stable","version":"v1.10.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.9.0","date":"2024-10-04T21:33:29Z","type":"stable","version":"v1.9.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.8.0","date":"2024-03-01T01:04:25Z","type":"stable","version":"v1.8.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.7.4","date":"2023-04-20T13:45:29Z","type":"stable","version":"v1.7.4"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.7.3","date":"2022-11-30T15:24:12Z","type":"stable","version":"v1.7.3"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.7.2","date":"2022-01-10T12:19:49Z","type":"stable","version":"v1.7.2"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.7.1","date":"2021-05-28T09:08:34Z","type":"stable","version":"v1.7.1"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.7.0","date":"2021-02-13T14:11:25Z","type":"stable","version":"v1.7.0"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.6.5","date":"2020-12-21T05:24:03Z","type":"stable","version":"v1.6.5"},{"url":"https://github.com/facebookresearch/faiss/releases/tag/v1.6.4","date":"2020-10-22T13:28:27Z","type":"stable","version":"v1.6.4"}]` | - |
| reliability.sla_pct | - | 99.95 |
| reliability.status_page | yes | yes |
| security.disclosure_policy | - | yes |
| security.gdpr | - | yes |
| security.hipaa | - | yes |
| security.scorecard | 6.1 | - |
| security.soc2 | - | yes |
| security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=faiss-cpu&per_page=100","last_12m":0,"max_severity":null}` | - |

## Capabilities (Vector Databases)

| Capability | Faiss | Turbopuffer |
|---|:--:|:--:|
| **Deployment** |  |  |
| Deployment | Self-hosted | Managed |
| Serverless / consumption pricing | ✗ | ✓ |
| **Index** |  |  |
| ANN index (HNSW / IVF / DiskANN / ScaNN / flat) | HNSW, IVF, PQ, multi-index, NSG | - |
| Distance metrics (cosine / dot / Euclidean) | Euclidean (L2), inner product, L1, Linf | - |
| **Query** |  |  |
| Metadata filtering | - | Pre-filter |
| Hybrid search (dense + sparse fusion) | - | ✓ |
| Built-in BM25 / lexical | - | ✓ |
| **Storage** |  |  |
| Quantization | Product | - |
| On-disk vs in-memory | Disk-backed | Tiered |
| **Scale** |  |  |
| Multi-tenancy (namespaces / collections / tenants) | - | ✓ |
| Horizontal scale | Single-node | Sharded / distributed |
| **Consistency** |  |  |
| Consistency | - | Tunable |
| **Licensing** |  |  |
| Licence class | Permissive OSS | Proprietary |
| **Classification** |  |  |
| Purpose-built vs feature-of-parent | Extension | Dedicated DBMS |

*Source: Vioscale. Generated 2026-09-01T15:18:18.862Z. "-" = undocumented, not absent.*