Milvus pricing

About

Milvus is the world’s most widely deployed open-source vector database, created by the engineers at Zilliz. The software is free under the Apache-2.0 license and is a graduated, top-level project of the Linux Foundation’s LF AI & Data Foundation — so the technology has no list price at all; self-hosters pay only for the compute, storage, and operational effort to run it.

Zilliz monetizes through Zilliz Cloud, the fully managed version of Milvus. This open-core split is the whole pricing story: the database is a commodity good given away to win developer mindshare, and the company captures revenue by removing the operational burden (cluster sizing, indexing, scaling, backups, compliance) of running vector search in production.

Zilliz raised a $60M Series B extension in August 2022 (on top of an earlier $43M), bringing total funding to roughly $113M, and relocated its headquarters to the San Francisco Bay Area to expand its engineering and go-to-market teams around the managed cloud.

For the most current information, visit Zilliz Cloud pricing and the Milvus project site.

Pricing summary : How Milvus’s pricing model works

There are two distinct cost worlds. Milvus OSS is free — your only costs are the cloud/server infrastructure and the engineering time to operate it. Zilliz Cloud (managed Milvus) is consumption-based, with a generous free tier and two paid cluster shapes:

• Free Tier — free: 5 GB storage, 2.5M vCUs/month, up to 5 collections.
• Serverless — pay-per-operation. Billed in virtual compute units (vCUs) for reads and writes, plus storage. Idle compute costs nothing (you still pay storage). Writes are metered by data volume inserted/deleted; reads carry a per-query vCU minimum that scales with data scanned and rows returned.
• Dedicated — reserved compute units (CUs) billed per CU-hour, with capacity- and performance-optimized CU types and annual-commit discounts.
• Enterprise / BYOC — Bring Your Own Cloud plus a Business Critical plan for regulated industries (cross-region backups, compliance, SLAs), quoted by sales.

(Exact per-unit rates are in the Hidden costs table and FAQ, sourced from Zilliz docs — the live pricing page was bot-blocked at capture time.)

What makes this different: Milvus separates the metering for writes (data volume inserted/deleted) from reads (query work + data scanned/returned) and lets Serverless drop idle compute to zero — so a low-traffic app with a large index pays almost nothing for compute and only the (now very cheap) storage line.

Pricing by product

Sales motions across products: PLG/self-serve for OSS, Free Tier and Serverless; sales-led for Dedicated at scale and Enterprise/BYOC. Exact per-unit rates live in the Hidden costs table and FAQ.

Hidden costs : What Milvus users actually pay

The real cost of Milvus depends almost entirely on whether you self-host or use the managed cloud:

• Self-hosted (OSS): the “free” software still costs you GPU/CPU instances, memory (HNSW indexes are memory-hungry), object storage, and — most underrated — engineering time. Community reports note teams running self-hosted Milvus for months before realizing ops cost more than a managed plan would have at their scale.
• Zilliz Cloud Serverless: the trap is read amplification — each read is a minimum of 6 vCUs and grows with data scanned and rows returned, so high query-per-second RAG workloads can run up vCU bills even with cheap storage.
• Storage and transfer: storage is now cheap ($0.04/GB/mo), but data transfer and audit logs are separately billed line items, and Dedicated CU-hours accrue whether or not the cluster is queried.

Want to estimate your own Milvus / Zilliz Cloud bill? Use the Milvus pricing calculator to model costs from your read/write and storage patterns.

Pricing evolution : Milvus pricing history and changes

Cadence

Tracked range: 2023–present, from Zilliz Cloud release notes and pricing-update blog posts. Public Wayback snapshots of the managed pricing page were not reliably available, so history is reconstructed from official release notes and announcements rather than archived captures.

Notable changes

• 2023-06-11 — Zilliz Cloud reaches general availability with a tiered model (Free, Dedicated from ~$99/mo, Serverless) and consumption-based billing.
• 2024 — Serverless consolidates on a pay-per-operation model billed in vCUs ($4 per million), charging only for read/write operations plus storage.
• 2025-10 — Tiered storage rebuild cuts storage 87% ($0.30 → $0.04/GB/month), reduces compute pricing ~25%, and adds cross-region backups + a Business Critical plan for regulated industries.
• 2026-01-01 — Storage pricing standardized at $0.04/GB/month across AWS, Azure and Google Cloud.

What’s unique : Milvus’s distinctive pricing mechanics

1. Open-core, two-priced. The product literally has two prices: $0 for the OSS engine, and consumption-based for the managed cloud. The free software is the funnel; the managed cloud is the business.

2. Read/write split metering. Serverless meters writes by data volume (0.25 vCU/KB inserted, 1 vCU/delete) and reads by query work (minimum 6 vCUs, scaling with scan + rows returned) — a finer-grained value metric than the per-pod or per-vector models rivals use.

3. Zero-cost idle. Serverless charges nothing for idle compute — only storage — so a large but rarely-queried index is cheap to keep online. The October 2025 object-storage-backed tiered architecture (S3 with >90% local cache hit rates) is what makes the $0.04/GB storage line economically credible.

Strengths & weaknesses

Billing UX : Milvus billing controls and transparency

• Billing controls — Free tier requires no credit card; Serverless and Dedicated offer 30-day free trials. Available on AWS Marketplace as pay-as-you-go for consolidated cloud billing.
• Usage visibility — The Zilliz Cloud console exposes cost by category (on-demand compute, Serverless operations, storage, storage requests, data transfer, audit logs) per the documented cost model.
• Payment options — Self-serve card for Free/Serverless/Dedicated; cloud-marketplace billing (AWS) and invoiced contracts with commit discounts for Enterprise/BYOC.

Strategic wins : Why Milvus’s pricing decisions worked

1. Give away the engine, sell the operations

By open-sourcing Milvus under Apache-2.0 and donating it to the LF AI & Data Foundation, Zilliz turned the database into a default choice for AI builders, then monetized the part developers actually dislike — running it. This is the classic open-core play applied to vector search. See usage-based pricing strategy for the underlying frameworks.

2. Lead the price-down race in vector storage

The October 2025 87% storage cut and ~25% compute reduction were a deliberate move to stay ahead as vector-DB pricing compresses. Re-architecting onto object storage with a hot cache let Zilliz cut the price while improving margins — a structural win, not just a discount. Related: how AI companies structure pricing and outcome-based pricing trends.

3. Pick value metrics that match the workload

Splitting metering into write-volume (vCU/KB) and read-work (vCU/query) ties the bill to the actual value-producing operations rather than to provisioned capacity. See choosing the right usage metric.

Areas to improve : Gaps in Milvus’s pricing approach

1. vCU forecasting is hard

The minimum-6-vCU-per-read rule plus scan/return scaling makes Serverless bills tough to predict for query-heavy RAG. A clearer per-query cost estimator up front would reduce bill-shock risk. See bill shock and cost unpredictability.

2. Too many metered dimensions

vCUs, CU-hours, storage, storage requests, data transfer, and audit logs are six separate lines. Bundling or simplifying for smaller customers would lower the cognitive cost of adoption.

3. The “free” trap for self-hosters

Marketing leans on “free and open-source,” but the total cost of self-hosting (memory-hungry indexes + ops) catches teams off guard. More honest TCO guidance vs. the managed cloud would build trust.

Key takeaways

1. Milvus is free; Zilliz Cloud is the product. Never conflate the OSS engine’s $0 license with the cost of running vector search in production.
2. Usage-based done well rewards idle. Serverless charging nothing for idle compute is a genuine UBP feature, not a gimmick — it suits spiky AI workloads.
3. Storage is racing to zero. The 87% storage cut shows vector-DB economics shifting from RAM-resident indexes to object-storage-backed tiers.
4. Metering granularity is a double-edged sword. Splitting read vs. write vCUs aligns price to value but makes forecasting harder.
5. Open-core seeds the funnel. Free OSS + a generous managed free tier is how Zilliz competes with closed rivals like Pinecone on adoption.

UBP implications

1. Charge for value-producing operations, not provisioned capacity. Milvus’s vCU/CU-hour split is a clean example of metering reads and writes separately.
2. Make idle free to win spiky workloads. Zero-cost idle Serverless compute is a strong UBP differentiator for unpredictable AI traffic.
3. Re-architect to cut price and protect margin. The object-storage tiered redesign let Zilliz drop storage 87% without bleeding margin — pricing power follows architecture.

Sources

• Zilliz Cloud pricing (accessed 2026-06-09)
• Understand Cost — Zilliz Cloud docs (accessed 2026-06-09)
• Serverless Cluster Cost — Zilliz Cloud docs (accessed 2026-06-09)
• Dedicated Cluster Cost — Zilliz Cloud docs (accessed 2026-06-09)
• New in Zilliz Cloud: Tiered Storage, BC Plan, Pricing Changes (Oct 2025) (accessed 2026-06-09)
• Zilliz Cloud free tier (accessed 2026-06-09)
• Zilliz raises $60M Series B extension — TechCrunch (Aug 2022) (accessed 2026-06-09)

Bottom line

Milvus is the rare AI-infra entry whose core product is genuinely free: the open-source vector database carries no license cost, and Zilliz makes money by managing it. Zilliz Cloud’s pricing is real usage-based — vCUs for spiky Serverless workloads, CU-hours for steady Dedicated clusters — with a generous free tier and an October 2025 re-architecture that cut storage 87% and compute ~25%. The catch is complexity: six metered dimensions and a per-read vCU minimum make bills hard to forecast, and the “free” OSS path quietly bills you in engineering time. Browse the pricing blueprint for more fully-researched company profiles.

Want to compare Milvus against other vector databases like Pinecone, Weaviate, and Qdrant? Browse the pricing blueprint.