Zilliz Cloud Limits

This page provides information about limits on the Zilliz Cloud platform. Submit a request to us if you need to report issues related to these limits.

Organizations, Projects & Members

The following table lists the limits on the maximum number of organizations and projects allowed for a single user.

Item	Max Number	Remarks
Organization	1	Zilliz Cloud automatically creates 1 organization upon successful account registration. If you need more organizations, please create a support ticket. A user can join multiple organizations.
Project	100	Each user can create up to 100 projects in 1 organization.
Organization and Project Member	100	An organization can hold up to 100 organization and project members in total.

API Keys

Item	Max Number	Remarks
API Key	100	Each organization can contain a maximum of 100 customized API keys for optimal resource utilization and security.

Clusters, CUs & vCUs

Clusters

The maximum number of clusters varies with your payment method and subscription plan.

• Without a valid payment method

  Subscription Plan	Max number	Remarks
  Free	1	Only 1 cluster is available for the Free cluster plan. You can drop an existing cluster and replace it with a new one if required.
  Serverless/Dedicated (Standard)/Dedicated (Enterprise)	1	You can only created 1 paid cluster in the free trial. If you would like additional clusters, please add a payment method.

• With a valid payment method

  Subscription Plan	Max number	Remarks
  Free	1	Only 1 cluster is available for the Free cluster plan. You can drop an existing cluster and replace it with a new one if required.
  Serverless	N/A	N/A
  Dedicated (Standard)/Dedicated (Enterprise)	Total CU size < 320	The maximum number of clusters in an organization depends on the total amount of cluster CUs. The accumulated number of CUs for all Dedicated clusters in an organization should not exceed 320.

CUs

A CU is the basic unit of compute resources used for parallel processing of data, and different CU types comprise varying combinations of CPU, memory, and storage. The concept of CU only applies to Dedicated clusters.

Subscription Plan	Limits	Remarks
Dedicated (Standard)	CU size * Replica Count <=32	On the console, you can create up to 32 CUs for a single cluster. However, the limit is CU size * Replica Count <=32 if replicas are added.
Dedicated (Enterprise)	CU size * Replica Count <=256	On the console, you can create up to 256 CUs for a single cluster. However, the limit is CU size * Replica Count <=256 if replicas are added.

You are welcome to contact us

• If your Dedicated (Standard)clusters require more than 32 CUs

• If your Dedicated (Enterprise) clusters require more than 256 CUs

vCUs

A virtual compute unit (vCU) is used to measure the resources consumed by read operations (such as search and query) and write operations (such as insert, upsert, and delete). The concept of vCU only applies to Free and Serverless clusters.

Subscription Plan	Limits
Free	2.5 million vCU per month
Serverless	N/A

Replicas

To add replicas, the cluster needs to have 8 CUs or more. The following limit applies as well.

Item	Limits	Remarks
Replica	10	You can create a maximum of 10 replicas.
Replica count * CU size	<= 256	The cluster CU size * Replica count should not exceed 256.

Databases

• Databases can only be created in Dedicated clusters.

• Each Dedicated cluster can have up to 1024 databases.

• Default database cannot be dropped.

Pipelines

Number of pipelines

The following table lists the limits on different types of pipelines you can create in a project.

Pipeline Type	Max. Number (Per Project)
Ingestion Pipeline	100
Deletion Pipeline	100
Search Pipeline	100

Ingestion

The following table lists the limits on customized chunk size supported in each embedding model.

Embedding Model	Chunk Size Range (Tokens）
zilliz/bge-base-en-v1.5	20-500
zilliz/bge-base-zh-v1.5	20-500
voyageai/voyage-2	20-3,000
voyageai/voyage-code-2	20-12,000
voyageai/voyage-large-2	20-12,000
openai/text-embedding-3-small	250-8,191
openai/text-embedding-3-large	250-8,191

The following table lists the limits on metadata fields generated by a PRESERVE function in an Ingestion Pipeline.

	Max. Number
Number of metadata fields	50
The max_length of a VARCHAR field	4,000

The following table lists the limits on the number of chunks that are allowed to be ingested each time.

Embedding Model	Max. Chunks/Ingestion
zilliz/bge-base-en-v1.5	3,500
voyageai/voyage-2	6,000
voyageai/voyage-code-2	6,000
openai/text-embedding-3-small	6,000
openai/text-embedding-large	6,000
zilliz/bge-base-zh-v1.5	3,500

Pipeline usage

	Max. Usage
Each organization	$20/month

Collections

Cluster Plan	Max Number	Remarks
Free cluster	5	You can create up to 5 collections.
Serverless cluster	100	You can create up to 100 collections.
Dedicated cluster	64 per CU, and <= 4096	You can create up to 64 collections per CU used in a dedicated cluster and no more than 4,096 collections in the cluster.

In addition to the limits on the number of collections per cluster, Zilliz Cloud also applies limits on consumed capacity. The following formula shows how Zilliz Cloud calculates the general capacity of a cluster. The consumed capacity should be less than the general capacity available.

General Capacity = 512 x Number of CUs

📘How can I know the general capacity of a cluster?

The general capacity of a cluster indicates the maximum physical resources allocated to the cluster, and it can be determined using the following formula:

<= 512 x Number of CUs

For instance,

• In a cluster of 2 CUs, you can create a maximum of 128 collections with a general capacity of 1,024.

• In a cluster of 12 CUs, you can create a maximum of 768 collections with a general capacity of 6,144.

• In a cluster of 32 CUs or more, you can create a maximum of 4,096 collections with a general capacity of 16,384.

📘How can I know the consumed capacity of a cluster?

The consumed capacity of a cluster indicates the physical resources consumed by the cluster.

For instance, let's assume that you have created 50 collections in a cluster; each of the first 20 collections has 20 partitions, while each of the remaining 30 collections has 10 partition. The consumed capacity of the cluster can be calculated as follows:

20 (collections) x 20 (partitions) + 30 (collections) x 10 (partitions) = 400 + 300 = 700

Based on the above calculation, Zilliz Cloud regards the cluster has a consumed capacity of 700.

Zilliz Cloud also imposed rate limits on collection operations including creating, loading, releasing, and dropping collections. The following rate limit applies to collections in both Serverless and Dedicated clusters.

	Rate Limit
Collection Operation (create, load, release, drop)	5 req/s per cluster

Partitions

Cluster Type	Max Number (Per Collection)	Remarks
Free cluster	1,024	You can create up to 1,024 partitions per collection in a free cluster.
Serverless cluster	1,024	You can create up to 1,024 partitions per collection in a serverless cluster.
Dedicated cluster	1,024	You can create up to 1,024 partitions per collection in a dedicated cluster.

When calculating the consumed and general capacity, refer to the notes in Collections. Additionally, the rate limit for creating partitions is 1 partition/s per cluster.

Fields

Item	Max Number
Fields per collection	64
Vector fields per collection	4

Other limits on fields:

• Null values are not supported by any field types.

• Some fields, such as VarChar or JSON, use more memory than expected and can cause the cluster to become full.

Dimensions

The maximum number of dimensions of a vector field is 32,768.

Operations

This section focuses on the rate limit for common data operations in Zilliz Cloud clusters.

Insert

Each insert request/response should be no greater than 64 MB.

The rate limit that applies varies with the cluster types and the number of CUs in use. The following table lists the rate limits for insert operations.

	Maximum Insert Rate Limits
Free cluster	2 MB/s
Serverless cluster	10 MB/s
Dedicated cluster 1 - 2 CUs	8 MB/s
Dedicated cluster 4 - 8 CUs	12 MB/s
Dedicated cluster 12 - 20 CUs	16 MB/s
Dedicated cluster [24 CUs, 64 CUs)	24 MB/s
Dedicated cluster [64 CUs, 128CUs)	36 MB/s
Dedicated cluster [128 CUs, 256CUs)	48 MB/s
Dedicated cluster >= 256 CUs	64 MB/s

When inserting data, include all schema-defined fields. Exclude the primary key if the collection has AutoID enabled.

To make inserted entities immediately retrievable in searches and queries, consider changing the consistency level in the search or query requests to Strong. Read Consistency Level for more.

Upsert

Each upsert request/response should be no greater than 64 MB.

The rate limit that applies varies with the cluster types and the number of CUs in use. The following table lists the rate limits for upsert operations.

	Maximum Upsert Rate Limits
Free cluster	2 MB/s
Serverless cluster	10 MB/s
Dedicated cluster 1 - 2 CUs	8 MB/s
Dedicated cluster 4 - 8 CUs	12 MB/s
Dedicated cluster 12 - 20 CUs	16 MB/s
Dedicated cluster [24 CUs, 64 CUs)	24 MB/s
Dedicated cluster [64 CUs, 128CUs)	36 MB/s
Dedicated cluster [128 CUs, 256CUs)	48 MB/s
Dedicated cluster >= 256 CUs	64 MB/s

When upserting data, include all schema-defined fields.

To make upserted entities immediately retrievable in searches and queries, consider changing the consistency level in the search or query requests to Strong. Read Consistency Level for more.

Index

Index types vary with field types. The following table lists the indexable field types and the corresponding index types.

Field Type	Index Type	Metric Type
Vector Field	AUTOINDEX	L2, IP, and COSINE
VarChar Field	TRIE	N/A
Int8/16/32/64	STL_SORT	N/A
Float32/64	STL_SORT	N/A

Flush

The rate limit for flush requests is 0.1 requests per second, imposed at the collection level for specific cluster types. This rate limit applies to:

• Serverless clusters compatible with Milvus 2.4.x or later.

• Dedicated clusters upgraded to the beta version, compatible with Milvus 2.4.x or later.

📘Notes

You are not advised to perform flush operations manually. Zilliz Cloud clusters handle it gracefully for you.

Load

The rate limit for load requests is 5 req/s per cluster.

📘Notes

You do not need to perform the load collection for collections that are already loaded, even if new data is coming into these collections.

Search

Each search request/response should be no greater than 64 MB.

The number of query vectors that each search request carries (usually known as nq) varies with your subscription plan:

• For Free and Serverless clusters, the nq is no greater than 10.

• For Dedicated clusters, the nq is no greater than 16,384.

The number that each search response carries (usually known as topK) varies with your subscription plan:

• For Free and Serverless clusters, the topK is no greater than 1,024 entities in return.

• For Dedicated clusters, the topK is no greater than 16,384 entities in return.

Query

Each query request/response should be no greater than 64 MB.

Each query response carries no more than 16,384 entities in return (usually known as topK).

Delete

Each delete request/response should be no greater than 64 MB.

The rate limit for delete requests is 0.5 MB/s per cluster.

Drop

The rate limit for drop requests is 5 req/s per cluster.

Data import

You can have up to 10 running or pending import jobs in a collection.

Zilliz Cloud also imposes limits on the files to import on the web console.

File Type	Local upload	Sync from S3/GCS/Other OSS
JSON	1 GB	1 GB
Numpy	Not support	The maximum size of the folder is 100 GB and the maximum size of each subdirectory is 15 GB
Parquet	Not support	10 GB

For details, refer to Prepare Source Data.

Backup on Console

Manually created backups are permanently retained.

The maximum retention period for automatically created backups is 30 days.

Restore on Console

You can restore a snapshot in the same region as the original cluster of the snapshot. The target cluster of the restoration should use the same CU type as the original one.

IP Access List

Item	Max Number	Remarks
IP Address (CIDR)	20	You can add up to 20 IP addresses to the allow list.