Understanding cost ↗

In this case, the August invoice would only show line items for each service you used (totaling $100). Since your usage exceeds the minimum usage commitment, you are only charged for your actual usage and no additional minimum usage line item appears on your invoice.

Discounts#

Pinecone offers a discount for customers who enroll in an annual plan with an upfront payment. Eligibility requires a minimum annual commitment of $8,000.

Throughout the contract term, the discount applies to List Price for all Pinecone services, excluding Storage and Support. Any usage that exceeds the prepaid credits will be billed at full List Price and will not qualify for the contractual discount.

Customers on the Standard and Enterprise pay-as-you-go plans may upgrade directly by navigating in the Pinecone console to Settings > Billing > Plans.

The self-serve annual plan is not available through cloud marketplace billing. To purchase an annual plan through a cloud marketplace, contact ar@pinecone.io.

Serverless indexes#

With serverless indexes, you pay for the amount of data stored and operations performed, based on three usage metrics: read units, write units, and storage.

For the latest serverless pricing rates, see Pricing.

Read units#

Read units (RUs) measure the compute, I/O, and network resources consumed by the following read requests:

• Query
• Fetch
• List

Read requests return the number of RUs used. You can use this information to monitor read costs.

Indexes built on Dedicated Read Nodes are not subject to read unit limits for query, fetch, and list operations. For sizing and capacity planning guidance, see the Dedicated Read Nodes guide.

Query#

The cost of a query scales linearly with the size of the targeted namespace. Specifically, a query uses 1 RU for every 1 GB of namespace size, with a minimum of 0.25 RUs per query.

To learn how to calculate your namespace size, see Storage.

Parameters that affect the size of the query response, such as top_k, include_metadata, and include_values, are not relevant for query cost; only the size of the namespace determines the number of RUs used.

Fetch#

A fetch request uses 1 RU for every 10 records fetched, for example:

Specifying a non-existent ID or adding the same ID more than once does not increase the number of RUs used. However, a fetch request will always use at least 1 RU.

Fetching records by metadata uses the same cost model as fetching by ID: 1 RU for every 10 records fetched.

List#

List has a fixed cost of 1 RU per call, with up to 100 records per call.

Write units#

Write units (WUs) measure the storage and compute resources used by the following write requests:

• Upsert
• Update
• Delete

Upsert#

An upsert request uses 1 WU for each 1 KB of the request, with a minimum of 5 WUs per request. When an upsert modifies an existing record, the request uses 1 WU for each 1 KB of the existing record as well.

For example, the following table shows the WUs used by upsert requests at different batch sizes and record sizes, assuming all records are new:

Update#

An update request uses 1 WU for each 1 KB of the new and existing record, with a minimum of 5 WUs per request.

For example, the following table shows the WUs used by an update at different record sizes:

Updating records by metadata uses the same cost model as updating by ID: 1 WU for each 1 KB of the new and existing record.

Delete#

A delete request uses 1 WU for each 1 KB of records deleted, with a minimum of 5 WUs per request.

For example, the following table shows the WUs used by delete requests at different batch sizes and record sizes:

Specifying a non-existent ID or adding the same ID more than once does not increase WU use.

Deleting a namespace or deleting all records in a namespace using deleteAll uses 5 WUs.

Deleting records by metadata uses the same cost model as deleting by ID: 1 WU for each 1 KB of records deleted.

Storage#

Storage costs are based on the size of an index on a per-gigabyte (GB) monthly rate. The size of an index is defined as the total size of its records across all namespaces. For the latest storage pricing rates, see Pricing.

A record can include a dense vector, a sparse vector, or both. Use the formula for your index type to calculate total size:

A dense index contains records with one dense vector each.

Dense index records can also contain sparse vectors (when the index metric is set to dotproduct), which can be useful for hybrid search. To learn how to calculate the size of a hybrid index, see Hybrid index.

Calculate dense index size (assuming no sparse vectors)

    Index size = Number of records × (
                   ID size + 
                   Metadata size +
                   Dense vector dimensions × 4 bytes
                 )
    ```

Where:

* `ID size` and `Metadata size` are measured in bytes, averaged across all records.
* Each `Dense vector dimension` uses 4 bytes.

**Example dense index calculations**

These examples assume 8-byte IDs:

| Records    | Dense vector dimensions | Avg metadata size | Index size |
| :--------- | :---------------------- | :---------------- | :--------- |
| 500,000    | 768                     | 500 bytes         | 1.79 GB    |
| 1,000,000  | 1536                    | 1,000 bytes       | 7.15 GB    |
| 5,000,000  | 1024                    | 15,000 bytes      | 95.5 GB    |
| 10,000,000 | 1536                    | 1,000 bytes       | 71.5 GB    |

<span class="callout-start" data-callout-type="note"></span>
  Example: 500,000 records × (8-byte ID + (768 dense vector dimensions × 4 bytes) + 500 bytes of metadata) = 1.79 GB
<span class="callout-end"></span>
<span class="tab-end"></span>

<span class="tab-start" data-tab-title="Sparse index"></span>
A [sparse index](/guides/index-data/indexing-overview#sparse-indexes) contains records with one sparse vector each.

**Calculate sparse index size**

  Index size = Number of records × (
                 ID size + 
                 Metadata size +
                 Number of non-zero sparse values × 8 bytes
               )
  ```

Where:

• ID size and Metadata size are measured in bytes, averaged across all records.
• Number of non-zero sparse values: Average number across all records. To find the count for a single record, check the length of the sparse vector’s indices or values array. Each non-zero value uses 8 bytes.

Example sparse index calculations

These examples assume 8-byte IDs:

Example: 500,000 records × (8-byte ID + (10 non-zero sparse values × 8 bytes) + 500 bytes of metadata) = 0.29 GB

A hybrid index contains records that each have one dense vector and an optional sparse vector.

Calculate hybrid index size

    Index size = Number of records × (
                   ID size + 
                   Metadata size +
                   Dense vector dimensions × 4 bytes + 
                   Number of non-zero sparse values × 8 bytes
                 )
    ```

Where:

* `ID size` and `Metadata size` are measured in bytes, averaged across all records.
* Each `Dense vector dimension` uses 4 bytes.
* `Number of non-zero sparse values`: Average number across all records, including those without sparse vectors. To find the count for a single record, check the length of the sparse vector's `indices` or `values` array. Each non-zero value uses 8 bytes.

**Example hybrid index calculations**

These examples assume 8-byte IDs:

| Records    | Dense vector dimensions | Avg number of non-zero sparse values | Avg metadata size | Index size |
| :--------- | :---------------------- | :----------------------------------- | :---------------- | :--------- |
| 500,000    | 768                     | 10                                   | 500 bytes         | 1.83 GB    |
| 1,000,000  | 1536                    | 50                                   | 1,000 bytes       | 7.54 GB    |
| 5,000,000  | 1024                    | 100                                  | 15,000 bytes      | 99.5 GB    |
| 10,000,000 | 1536                    | 50                                   | 1,000 bytes       | 75.4 GB    |

<span class="callout-start" data-callout-type="note"></span>
  Example: 500,000 records × (8-byte ID + (768 dense vector dimensions × 4 bytes) + (10 non-zero sparse values × 8 bytes) + 500 bytes of metadata) = 1.83 GB
<span class="callout-end"></span>
<span class="tab-end"></span>
<span class="tab-group-end"></span>


## Imports

[Importing from object storage](/guides/index-data/import-data) is the most efficient and cost-effective method to load large numbers of records into an index. The cost of an import is based on the size of the records read, whether the records were imported successfully or not.

If the import operation fails (e.g., after encountering a vector of the wrong dimension in an import with `on_error="abort"`), you will still be charged for the records read. However, if the import fails because of an internal system error, you will not incur charges. In this case, the import will return the error message `"We were unable to process your request. If the problem persists, please contact us at https://support.pinecone.io"`.

For the latest import pricing rates, see [Pricing](https://www.pinecone.io/pricing/).

## Backups and restores

A [backup](/guides/manage-data/backups-overview) is a static copy of a serverless index. Both the cost of storing a backup and [restoring an index](/guides/manage-data/restore-an-index) from a backup is based on the size of the index. For the latest backup and restore pricing rates, see [Pricing](https://www.pinecone.io/pricing/).

## Embedding

Pinecone hosts several [embedding models](/guides/index-data/create-an-index#embedding-models) so it's easy to manage your vector storage and search process on a single platform. You can use a hosted model to embed your data as an integrated part of upserting and querying, or you can use a hosted model to embed your data as a standalone operation.

Embedding costs are determined by how many [tokens](https://www.pinecone.io/learn/tokenization/) are in a request. In general, the more words contained in your passage or query, the more tokens you generate.

For example, if you generate embeddings for the query, "What is the maximum diameter of a red pine?", Pinecone Inference generates 10 tokens, then converts them into an embedding. If the price per token for your billing plan is \$.08 per million tokens, then this API call costs \$.00001.

To learn more about tokenization, see [Choosing an embedding model](https://www.pinecone.io/learn/series/rag/embedding-models-rundown/). For the latest embed pricing rates, see [Pricing](https://www.pinecone.io/pricing/).

<span class="callout-start" data-callout-type="tip"></span>
Embedding requests returns the total tokens generated. You can use this information to [monitor and manage embedding costs](/guides/manage-cost/monitor-usage-and-costs#embedding-tokens).
<span class="callout-end"></span>

## Reranking

Pinecone hosts several [reranking models](/guides/search/rerank-results#reranking-models) so it's easy to manage two-stage vector retrieval on a single platform. You can use a hosted model to rerank results as an integrated part of a query, or you can use a hosted model to rerank results as a standalone operation.

Reranking costs are determined by the number of requests to the reranking model. For the latest rerank pricing rates, see [Pricing](https://www.pinecone.io/pricing/).

## Assistant

For details on how costs are incurred in Pinecone Assistant, see [Assistant pricing](/guides/assistant/pricing-and-limits).

## HIPAA compliance add-on

Full HIPAA compliance is included with the [Enterprise plan](https://www.pinecone.io/pricing/).

For **Standard plan** customers, HIPAA compliance is available as an optional add-on for **\$190 per month**. The add-on is billed monthly and added to your regular invoice. A 6-month minimum period is required.

The HIPAA compliance add-on includes:

* HIPAA-ready infrastructure
* Encrypted data storage
* Audit logging
* Enhanced security controls
* BAA execution and compliance documentation support

<span class="callout-start" data-callout-type="note"></span>
If you upgrade to the Enterprise plan, the HIPAA compliance add-on is automatically removed because HIPAA compliance is included with Enterprise.
<span class="callout-end"></span>

### Enable the HIPAA compliance add-on

To enable the HIPAA compliance add-on, [contact sales](mailto:sales@pinecone.io) or [submit a request](https://www.pinecone.io/contact/?contact_form_inquiry_type=Sales). The Pinecone team will review your request and guide you through activation.

## See also

* [Manage cost](/guides/manage-cost/manage-cost)
* [Monitor usage](/guides/manage-cost/monitor-usage-and-costs)
* [Pricing](https://www.pinecone.io/pricing/)