Skip to main content
Version: User Guides (Cloud)

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.

ItemMax numberRemarks
Organization1
Each user can create only one organization.
Organization member100An organization can hold up to 100 members. A user can belong to multiple organizations.
Project10Each user can create 10 projects.
Project Member100A project can hold up to 100 members. A user can belong to multiple projects within their organization.

Clusters & CUs

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

  • Without a valid payment method

    Subscription PlanMax numberRemarks
    Serverless Cluster1Only 1 cluster is available for the Free Serverless cluster plan. You can drop an existing cluster and replace it with a new one if requird.
    Standard Cluster1
    The Trial Standard Cluster plan offers only 1 cluster. If you would like additional clusters, please provide payment.
    Enterprise Cluster0
  • With a valid payment method

    Subscription PlanLimitsRemarks
    Standard Cluster128 CUsOn the console, you can create up to 128 compute units (CUs) across all Standard Clusters or 32 CUs for a single cluster.
    Enterprise Cluster128 CUsOn the console, you can create up to 128 compute units (CUs) across all Enterprise Clusters or 32 CUs for a single cluster.

You are welcome to contact us

  • If one of your clusters needs more than 32 CUs or,

  • If all your Enterprise Clusters require more than 128 CUs.

Pipelines

Number of pipelines

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

Pipeline TypeMax. Number (Per Project)
Ingestion Pipeline10
Deletion Pipeline10
Search Pipeline10

Ingestion

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

Embedding ModelChunk Size Range (Tokens)
zilliz/bge-base-en-v1.520-500
zilliz/bge-base-zh-v1.520-500
voyageai/voyage-220-3,000
voyageai/voyage-code-220-12,000
voyageai/voyage-large-220-12,000
openai/text-embedding-3-small250-8,191
openai/text-embedding-3-large250-8,191

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

Max. Number
Number of metadata fields5
The max_length of a VARCHAR field4,000

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

Embedding ModelMax. Chunks/Ingestion
zilliz/bge-base-en-v1.53,500
voyageai/voyage-26,000
voyageai/voyage-code-26,000
openai/text-embedding-3-small6,000
openai/text-embedding-large6,000
zilliz/bge-base-zh-v1.53,500

Token usage

The following table lists the limits on token usage.

Pipeline TypeEmbedding ModelMax. Token Usage
Ingestion Pipelineopenai/text-embedding-3-small & openai/text-embedding-3-large80,000,000
Others100,000,000
Search Pipelineopenai/text-embedding-3-small & openai/text-embedding-3-large30,000,000
Others20,000,000
All Pipelines in an Organizationopenai/text-embedding-3-small & openai/text-embedding-3-large150,000,000
Others200,000,000
📘Notes

For the maximum token usage of all pipelines in an organization, the token usage of a dropped pipeline is still included in the overall count.

Collections

Cluster TypeMax NumberRemarks
Serverless cluster2
You can create up to 2 serverless collections.
Dedicated cluster
64 per CU, and <= 4096You 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 table lists the limits on the general capacity of a cluster.

Number of CUsGeneral Capacity
1-8 CUs<= 4,096
12 CUs and more<= 512 x Number of CUs

The consumed capacity should be less than the general capacity available.

📘Notes

The following explains how Zilliz Cloud calculates the consumed capacity and general capacity of a cluster.

  • Calculating the consumed capacity in a 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.

  • Calculating the general capacity of a cluster

The general capacity 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 65,536.

Additionally, the rate limit for creating collections is 1 collection/s per cluster.

Partitions

Cluster TypeMax number (Per collection)Remarks
Serverless cluster64
You can create up to 64 partitions per collection in a serverless cluster.
Dedicated cluster
4,096You can create up to 4,096 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

ItemMax NumberRemarks
Fields per collection64N/A
Vector fields per collection1The support for multiple vector fields is coming soon.

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.

Insert rate limits
Serverless cluster2 MB/s
Dedicated cluster 1 CU and 2 CUs4 MB/s
Dedicated cluster 4 - 8 CUs6 MB/s
Dedicated cluster 12 - 20 CUs8 MB/s
Dedicated cluster >= 24 CUs12 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.

Insert rate limits
Serverless cluster2 MB/s
Dedicated cluster 1 CU and 2 CUs4 MB/s
Dedicated cluster 4 - 8 CUs6 MB/s
Dedicated cluster 12 - 20 CUs8 MB/s
Dedicated cluster >= 24 CUs12 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 TypeIndex TypeMetric Type
Vector FieldAUTOINDEXL2, IP, and COSINE
VarChar FieldTRIEN/A
Int8/16/32/64STL_SORTN/A
Float32/64STL_SORTN/A

Flush

The rate limit for flush requests is 1 req/s per cluster.

📘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 1 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.

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

Each search request carries no more than__ 16,384__ query vectors (usually known as nq).

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

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 1 req/s per cluster.

CU Capacity

Read Select the Right CU for more.

Data Import on Console

File TypeLocal uploadSync from S3/GCS/Other OSS
JSON1 GB1 GB
Numpy
Not supportThe maximum size of the folder is 100 GB and the maximum size of each subdirectory is 15 GB
ParquetNot support10GB

For details, refer to Prepare Source Data.

Backup on Console

Zilliz Cloud provides free storage for backup snapshots for up to 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.