This page describes different types of limits for Pinecone Database.
Rate limits are restrictions on the frequency of requests within a specified period of time. Rate limits vary based on pricing plan and apply to serverless indexes only.
Metric | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
Read units per month per project | 1,000,000 | Unlimited | Unlimited |
Write units per month per project | 2,000,000 | Unlimited | Unlimited |
Upsert size per second per namespace | 50 MB | 50 MB | 50 MB |
Query read units per second per index | 2,000 | 2,000 | 2,000 |
Update records per second per namespace | 100 | 100 | 100 |
Fetch requests per second per index | 100 | 100 | 100 |
List requests per second per index | 200 | 200 | 200 |
Describe index stats requests per second per index | 100 | 100 | 100 |
Delete records per second per namespace | 5,000 | 5,000 | 5,000 |
Delete records per second per index | 5,000 | 5,000 | 5,000 |
Embedding tokens per minute per model | Model-specific | Model-specific | Model-specific |
Embedding tokens per month per model | 5,000,000 | Unlimited | Unlimited |
Rerank requests per minute per model | Model-specific | Model-specific | Model-specific |
Rerank requests per month per model | 500 | Model-specific | Model-specific |
Starter plan | Standard plan | Enterprise plan |
---|---|---|
1,000,000 | Unlimited | Unlimited |
Read units measure the compute, I/O, and network resources used by fetch, query, and list requests to serverless indexes. When you reach the monthly read unit limit for a project, fetch, query, and list requests to serverless indexes in the project will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To continue reading from serverless indexes in the project, upgrade your plan.
To check how close you are to the monthly read unit limit for a project, do the following:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2,000,000 | Unlimited | Unlimited |
Write units measure the storage and compute resources used by upsert, update, and delete requests to serverless indexes. When you reach the monthly write unit limit for a project, upsert, update, and delete requests to serverless indexes in the project will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To continue writing data to serverless indexes in the project, upgrade your plan.
To check how close you are to the monthly read unit limit for a project, do the following:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
50 MB | 50 MB | 50 MB |
When you reach the per second upsert size for a namespace in an index, additional upserts will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2,000 | 2,000 | 2,000 |
Pinecone measures query usage in read units. When you reach the per second limit for queries across all namespaces in an index, additional queries will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
To check how many read units a query consumes, check the query response.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second update limit for a namespace in an index, additional updates will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second fetch limit across all namespaces in an index, additional fetch requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
200 | 200 | 200 |
When you reach the per second list limit across all namespaces in an index, additional list requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second describe index stats limit across all namespaces in an index, additional list requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5000 | 5000 | 5000 |
When you reach the per second delete limit for a namespace in an index, additional deletes will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5000 | 5000 | 5000 |
When you reach the per second delete limit across all namespaces in an index, additional deletes will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Embedding model | Input type | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|---|
llama-text-embed-v2 | Passage | 250,000 | 1,000,000 | 1,000,000 |
Query | 50,000 | 250,000 | 250,000 | |
multilingual-e5-large | Passage | 250,000 | 1,000,000 | 1,000,000 |
Query | 50,000 | 250,000 | 250,000 | |
pinecone-sparse-english-v0 | Passage | 250,000 | 3,000,000 | 3,000,000 |
Query | 250,000 | 3,000,000 | 3,000,000 |
When you reach the per minute token limit for an embedding model hosted by Pinecone, additional embeddings will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5,000,000 | Unlimited | Unlimited |
When you reach the monthly token limit for an embedding model hosted by Pinecone, additional embeddings will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan or contact Support.
Reranking model | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
cohere-rerank-3.5 | Not available | 300 | 300 |
bge-reranker-v2-m3 | 60 | 60 | 60 |
pinecone-rerank-v0 | 60 | 60 | 60 |
When you reach the per minute request limit for a reranking model hosted by Pinecone, additional reranking requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan.
Reranking model | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
cohere-rerank-3.5 | Not available | Unlimited | Unlimited |
bge-reranker-v2-m3 | 500 | Unlimited | Unlimited |
pinecone-rerank-v0 | 500 | Unlimited | Unlimited |
When you reach the monthly request limit for a reranking model hosted by Pinecone, additional reranking requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan or contact Support.
Object limits are restrictions on the number or size of objects in Pinecone. Object limits vary based on pricing plan.
Metric | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
Projects per organization | 1 | 20 | 100 |
Pods per organization | 0 | 100 | 100 |
Serverless indexes per project 1 | 5 | 20 | 200 |
Serverless index storage per project | 2 GB | N/A | N/A |
Namespaces per serverless index | 100 | 25,000 | 100,000 |
Serverless backups per project | N/A | 500 | 1000 |
Namespaces per serverless backup | N/A | 2000 | 2000 |
Pod-based indexes per project | 0 | N/A | N/A |
Pods per project 2 | 0 | 2 | 2 |
Collections per project | 100 | N/A | N/A |
us-east-1
region of AWS.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
1 | 20 | 100 |
When you reach this quota for an organization, trying to create projects will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan or contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | 100 | 100 |
When you reach this quota for an organization, trying to create pod-based indexes in any project in the organization will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5 | 20 | 200 |
When you reach this quota for a project, trying to create serverless indexes in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
On the Starter plan, all serverless must be in the us-east-1
region of AWS. To create indexes in different regions or to increase this quota, upgrade your plan or contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2 GB | N/A | N/A |
When you’ve reached this quota for a project, updates and upserts into serverless indexes will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To continue writing data into your serverless indexes, delete records to bring you under the limit or upgrade your plan.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 25,000 | 100,000 |
When you reach this quota for a serverless index, trying to upsert records into a new namespace in the index will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan.
These quotas are intended to provide reasonable boundaries and prevent unexpected or unintentional misuse. To increase your quota beyond the standard allotment, contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
N/A | 500 | 1000 |
When you reach this quota for a project, trying to create serverless backups in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
N/A | 2000 | 2000 |
When you reach this quota for a backup, trying to create serverless backups will fail and return a 403 - QUOTA_EXCEEDED
status.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | N/A | N/A |
When you try to create a pod-based index on the Starter plan, the request will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To create pod-based indexes, upgrade your plan.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | 2 | 2 |
When you reach this quota for a project, trying to create pod-based indexes in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To set or change the default limit, set a project pod limit.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | N/A | N/A |
When you reach this quota for a project, trying to create collections in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan.
Operation limits are restrictions on the size, number, or other characteristics of operations in Pinecone. Operation limits are fixed and do not vary based on pricing plan.
Metric | Limit |
---|---|
Max batch size | 2 MB or 1000 records with vectors 96 records with text |
Max metadata size per record | 40 KB |
Max length for a record ID | 512 characters |
Max dimensionality for dense vectors | 20,000 |
Max non-zero values for sparse vectors | 2048 |
Max dimensionality for sparse vectors | 4.2 billion |
Metric | Limit |
---|---|
Max top_k value | 10,000 |
Max result size | 4MB |
The query result size is affected by the dimension of the dense vectors and whether or not dense vector values and metadata are included in the result.
If a query fails due to exceeding the 4MB result size limit, choose a lower top_k
value, or use include_metadata=False
or include_values=False
to exclude metadata or values from the result.
Limit | |
---|---|
Max records per fetch request | 1,000 |
Delete | Limit |
---|---|
Max records per delete request | 1,000 |
An identifier is a string of characters (up to 255 characters in length) used to identify “named” objects in Pinecone. The following Pinecone objects use strings as identifiers:
Object | Field | Max # characters | Allowed characters |
---|---|---|---|
Organization | name | 512 | UTF-8 except \0 |
Project | name | 512 | UTF-8 except \0 |
Index | name | 45 | A-Z , a-z , 0-9 , and - |
Namespace | namespace | 512 | ASCII except \0 |
Record | id | 512 | ASCII except \0 |
This page describes different types of limits for Pinecone Database.
Rate limits are restrictions on the frequency of requests within a specified period of time. Rate limits vary based on pricing plan and apply to serverless indexes only.
Metric | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
Read units per month per project | 1,000,000 | Unlimited | Unlimited |
Write units per month per project | 2,000,000 | Unlimited | Unlimited |
Upsert size per second per namespace | 50 MB | 50 MB | 50 MB |
Query read units per second per index | 2,000 | 2,000 | 2,000 |
Update records per second per namespace | 100 | 100 | 100 |
Fetch requests per second per index | 100 | 100 | 100 |
List requests per second per index | 200 | 200 | 200 |
Describe index stats requests per second per index | 100 | 100 | 100 |
Delete records per second per namespace | 5,000 | 5,000 | 5,000 |
Delete records per second per index | 5,000 | 5,000 | 5,000 |
Embedding tokens per minute per model | Model-specific | Model-specific | Model-specific |
Embedding tokens per month per model | 5,000,000 | Unlimited | Unlimited |
Rerank requests per minute per model | Model-specific | Model-specific | Model-specific |
Rerank requests per month per model | 500 | Model-specific | Model-specific |
Starter plan | Standard plan | Enterprise plan |
---|---|---|
1,000,000 | Unlimited | Unlimited |
Read units measure the compute, I/O, and network resources used by fetch, query, and list requests to serverless indexes. When you reach the monthly read unit limit for a project, fetch, query, and list requests to serverless indexes in the project will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To continue reading from serverless indexes in the project, upgrade your plan.
To check how close you are to the monthly read unit limit for a project, do the following:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2,000,000 | Unlimited | Unlimited |
Write units measure the storage and compute resources used by upsert, update, and delete requests to serverless indexes. When you reach the monthly write unit limit for a project, upsert, update, and delete requests to serverless indexes in the project will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To continue writing data to serverless indexes in the project, upgrade your plan.
To check how close you are to the monthly read unit limit for a project, do the following:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
50 MB | 50 MB | 50 MB |
When you reach the per second upsert size for a namespace in an index, additional upserts will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2,000 | 2,000 | 2,000 |
Pinecone measures query usage in read units. When you reach the per second limit for queries across all namespaces in an index, additional queries will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
To check how many read units a query consumes, check the query response.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second update limit for a namespace in an index, additional updates will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second fetch limit across all namespaces in an index, additional fetch requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
200 | 200 | 200 |
When you reach the per second list limit across all namespaces in an index, additional list requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 100 | 100 |
When you reach the per second describe index stats limit across all namespaces in an index, additional list requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To handle this limit, automatically retry requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5000 | 5000 | 5000 |
When you reach the per second delete limit for a namespace in an index, additional deletes will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5000 | 5000 | 5000 |
When you reach the per second delete limit across all namespaces in an index, additional deletes will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Embedding model | Input type | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|---|
llama-text-embed-v2 | Passage | 250,000 | 1,000,000 | 1,000,000 |
Query | 50,000 | 250,000 | 250,000 | |
multilingual-e5-large | Passage | 250,000 | 1,000,000 | 1,000,000 |
Query | 50,000 | 250,000 | 250,000 | |
pinecone-sparse-english-v0 | Passage | 250,000 | 3,000,000 | 3,000,000 |
Query | 250,000 | 3,000,000 | 3,000,000 |
When you reach the per minute token limit for an embedding model hosted by Pinecone, additional embeddings will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan. Otherwise, you can handle this limit by automatically retrying requests with an exponential backoff.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5,000,000 | Unlimited | Unlimited |
When you reach the monthly token limit for an embedding model hosted by Pinecone, additional embeddings will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan or contact Support.
Reranking model | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
cohere-rerank-3.5 | Not available | 300 | 300 |
bge-reranker-v2-m3 | 60 | 60 | 60 |
pinecone-rerank-v0 | 60 | 60 | 60 |
When you reach the per minute request limit for a reranking model hosted by Pinecone, additional reranking requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan.
Reranking model | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
cohere-rerank-3.5 | Not available | Unlimited | Unlimited |
bge-reranker-v2-m3 | 500 | Unlimited | Unlimited |
pinecone-rerank-v0 | 500 | Unlimited | Unlimited |
When you reach the monthly request limit for a reranking model hosted by Pinecone, additional reranking requests will fail and return a 429 - TOO_MANY_REQUESTS
status with the following error:
To increase this limit, upgrade your plan or contact Support.
Object limits are restrictions on the number or size of objects in Pinecone. Object limits vary based on pricing plan.
Metric | Starter plan | Standard plan | Enterprise plan |
---|---|---|---|
Projects per organization | 1 | 20 | 100 |
Pods per organization | 0 | 100 | 100 |
Serverless indexes per project 1 | 5 | 20 | 200 |
Serverless index storage per project | 2 GB | N/A | N/A |
Namespaces per serverless index | 100 | 25,000 | 100,000 |
Serverless backups per project | N/A | 500 | 1000 |
Namespaces per serverless backup | N/A | 2000 | 2000 |
Pod-based indexes per project | 0 | N/A | N/A |
Pods per project 2 | 0 | 2 | 2 |
Collections per project | 100 | N/A | N/A |
us-east-1
region of AWS.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
1 | 20 | 100 |
When you reach this quota for an organization, trying to create projects will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan or contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | 100 | 100 |
When you reach this quota for an organization, trying to create pod-based indexes in any project in the organization will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
5 | 20 | 200 |
When you reach this quota for a project, trying to create serverless indexes in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
On the Starter plan, all serverless must be in the us-east-1
region of AWS. To create indexes in different regions or to increase this quota, upgrade your plan or contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
2 GB | N/A | N/A |
When you’ve reached this quota for a project, updates and upserts into serverless indexes will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To continue writing data into your serverless indexes, delete records to bring you under the limit or upgrade your plan.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | 25,000 | 100,000 |
When you reach this quota for a serverless index, trying to upsert records into a new namespace in the index will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan.
These quotas are intended to provide reasonable boundaries and prevent unexpected or unintentional misuse. To increase your quota beyond the standard allotment, contact Support.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
N/A | 500 | 1000 |
When you reach this quota for a project, trying to create serverless backups in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
Starter plan | Standard plan | Enterprise plan |
---|---|---|
N/A | 2000 | 2000 |
When you reach this quota for a backup, trying to create serverless backups will fail and return a 403 - QUOTA_EXCEEDED
status.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | N/A | N/A |
When you try to create a pod-based index on the Starter plan, the request will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To create pod-based indexes, upgrade your plan.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
0 | 2 | 2 |
When you reach this quota for a project, trying to create pod-based indexes in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To set or change the default limit, set a project pod limit.
Starter plan | Standard plan | Enterprise plan |
---|---|---|
100 | N/A | N/A |
When you reach this quota for a project, trying to create collections in the project will fail and return a 403 - QUOTA_EXCEEDED
status with the following error:
To increase this quota, upgrade your plan.
Operation limits are restrictions on the size, number, or other characteristics of operations in Pinecone. Operation limits are fixed and do not vary based on pricing plan.
Metric | Limit |
---|---|
Max batch size | 2 MB or 1000 records with vectors 96 records with text |
Max metadata size per record | 40 KB |
Max length for a record ID | 512 characters |
Max dimensionality for dense vectors | 20,000 |
Max non-zero values for sparse vectors | 2048 |
Max dimensionality for sparse vectors | 4.2 billion |
Metric | Limit |
---|---|
Max top_k value | 10,000 |
Max result size | 4MB |
The query result size is affected by the dimension of the dense vectors and whether or not dense vector values and metadata are included in the result.
If a query fails due to exceeding the 4MB result size limit, choose a lower top_k
value, or use include_metadata=False
or include_values=False
to exclude metadata or values from the result.
Limit | |
---|---|
Max records per fetch request | 1,000 |
Delete | Limit |
---|---|
Max records per delete request | 1,000 |
An identifier is a string of characters (up to 255 characters in length) used to identify “named” objects in Pinecone. The following Pinecone objects use strings as identifiers:
Object | Field | Max # characters | Allowed characters |
---|---|---|---|
Organization | name | 512 | UTF-8 except \0 |
Project | name | 512 | UTF-8 except \0 |
Index | name | 45 | A-Z , a-z , 0-9 , and - |
Namespace | namespace | 512 | ASCII except \0 |
Record | id | 512 | ASCII except \0 |