# turbopuffer

> Serverless vector and full-text search on object storage.

turbopuffer has a SharkScore of 67.1/100, ranked #14 of 53 in Vector databases (updated 2026-11-19).

- Website: https://turbopuffer.com (turbopuffer.com)
- Kind: Tool · Pricing: Paid · from $16/mo
- Maker: turbopuffer
- Categories: Vector databases
- Verified by the maker: no

## Why it scores 67.1

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 52 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 65 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Vector databases.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | #283.4K |
| GitHub stars | — |
| Stars, last 90 days | — |
| Downloads, 30 days | 13.7M |
| Reviews | none yet |
| Last update | — |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / no / yes / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, turbopuffer is a vector and full-text search database built on object storage; its docs note higher write latency and occasional slow cold queries [E1][E3].

turbopuffer is a hosted search database for vector, full-text, and hybrid search. The vendor describes an architecture using object storage for state and NVMe SSD with memory caching for compute [E3].

### Pros

- The docs list vector, full-text, hybrid, filter, and regex search features.
- The vendor offers multi-tenant, single-tenant, and BYOC deployment options.
- The pricing page lists a $16/month minimum-usage Launch plan.

### Cons

- The vendor documents higher write latency: p90 248 ms for 512 KB upserts.
- The vendor documents occasional cold queries, with p90 1,214 ms on 1 million documents for uncached or unpinned data.
- The Enterprise plan has a listed minimum of at least $4,096/month and a 35% usage premium.
- No free plan or free trial stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| launch | $16/month minimum usage | Includes all database features; multi-tenancy; community Slack and email support. |
| scale | $256/month minimum usage | Includes all database features; multi-tenancy; HIPAA-ready BAA, SSO, audit logs, IP allowlisting, private Slack channel, and support hours 8-5. Audit Log Streams are +$128/mo. |
| enterprise | >= $4,096/month; Contact us | 35% usage premium. Includes all database features; multi-tenancy, single-tenancy, and BYOC; private networking and CMEK; 24/7 support hours, support SLA, and 99.95% uptime SLA. Audit Log Streams are +$128/mo. |

Checked 2026-11-18 · https://turbopuffer.com/pricing

### Sources

- https://turbopuffer.com/ (fetched 2026-11-18)
- https://turbopuffer.com/pricing (fetched 2026-11-18)
- https://turbopuffer.com/docs (fetched 2026-11-18)
- https://turbopuffer.com/privacy-policy (fetched 2026-11-18)
- https://turbopuffer.com/terms-of-service (fetched 2026-11-18)
- https://turbopuffer.com/docs/security (fetched 2026-11-18)

## Top alternatives

1. [Supabase](https://rankshark.pro/tools/supabase) — SharkScore 78.9. Postgres platform with pgvector, auth and storage.
2. [Redis](https://rankshark.pro/tools/redis) — SharkScore 75.3. In-memory data store with vector search for AI apps.
3. [OpenSearch](https://rankshark.pro/tools/opensearch) — SharkScore 73.7. Open-source search and analytics with a vector engine.
4. [pgvector](https://rankshark.pro/tools/pgvector) — SharkScore 73.7. Vector similarity search for Postgres.
5. [Qdrant](https://rankshark.pro/tools/qdrant) — SharkScore 71.3. Fast open-source vector search, self-hosted or cloud.

---
Source: https://rankshark.pro/tools/turbopuffer · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
