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 | Each user can create only one organization. |
| Organization member | 100 | An organization can hold up to 100 members. A user can belong to multiple organizations. |
| Project | 10 | Each user can create 10 projects. |
| Project Member | 100 | A 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 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 1 The trial Serverless cluster plan offers only 1 cluster. If you would like additional clusters, please provide payment. Dedicated (Standard) 1 The trial Dedicated (Standard) cluster plan offers only 1 cluster. If you would like additional clusters, please provide payment. Dedicated (Enterprise) 0 -
With a valid payment method
Subscription Plan Limits Remarks Dedicated (Standard) 128 CUs On the console, you can create up to 128 compute units (CUs) across all Dedicated (Standard) Clusters or 24 CUs for a single cluster. Dedicated (Enterprise) 128 CUs On the console, you can create up to 128 compute units (CUs) across all Dedicated (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 Dedicated (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 Type | Max. Number (Per Project) |
|---|---|
| Ingestion Pipeline | 10 |
| Deletion Pipeline | 10 |
| Search Pipeline | 10 |
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 |
Token usage
The following table lists the limits on token usage.
| Pipeline Type | Embedding Model | Max. Token Usage |
|---|---|---|
| Ingestion Pipeline | openai/text-embedding-3-small & openai/text-embedding-3-large | 80,000,000 |
| Others | 100,000,000 | |
| Search Pipeline | openai/text-embedding-3-small & openai/text-embedding-3-large | 30,000,000 |
| Others | 20,000,000 | |
| All Pipelines in an Organization | openai/text-embedding-3-small & openai/text-embedding-3-large | 150,000,000 |
| Others | 200,000,000 |
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 Plan | Max Number | Remarks |
|---|---|---|
| Free cluster | 2 | You can create up to 2 collections. |
| Serverless cluster | 10 | You can create up to 10 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 table lists the limits on the general capacity of a cluster.
| Number of CUs | General 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.
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 Type | Max number (Per collection) | Remarks |
|---|---|---|
| Free cluster | 64 | You can create up to 64 partitions per collection in a free cluster. |
| Serverless cluster | 64 | You can create up to 64 partitions per collection in a serverless cluster. |
| Dedicated cluster | 4,096 | You 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
| Item | Max Number | Remarks |
|---|---|---|
| Fields per collection | 64 | N/A |
| Vector fields per collection | 1 | The 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 | |
|---|---|
| Free cluster | 2 MB/s |
| Serverless cluster | 100 MB/s |
| Dedicated cluster 1 CU and 2 CUs | 4 MB/s |
| Dedicated cluster 4 - 8 CUs | 6 MB/s |
| Dedicated cluster 12 - 20 CUs | 8 MB/s |
| Dedicated cluster >= 24 CUs | 12 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 | |
|---|---|
| Free cluster | 2 MB/s |
| Serverless cluster | 100 MB/s |
| Dedicated cluster 1 CU and 2 CUs | 4 MB/s |
| Dedicated cluster 4 - 8 CUs | 6 MB/s |
| Dedicated cluster 12 - 20 CUs | 8 MB/s |
| Dedicated cluster >= 24 CUs | 12 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 1 req/s per cluster.
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.
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.
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.
Data import
You can have up to 10 running or pending import jobs in a collection.
CU Capacity
Read Select the Right CU for more.
Data Import on 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 | 10GB |
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.