> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lambdadb.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Understanding costs

> Learn how LambdaDB serverless pricing works across read usage, write usage, storage, and inference usage. Covers per-request minimums, consistency surcharges, and managed embedding usage.

LambdaDB offers a **Free** plan and a **Standard** plan.

There is **no minimum cost** or base fee. If you have no usage, your cost is **\$0**.

On the **Standard** plan, usage is metered in four dimensions: **read usage**, **write usage**, **storage usage**, and **inference usage**. Charges are based on actual measured usage at the rates below.

For the latest pricing details, see [Pricing](https://lambdadb.ai/pricing).

## Plans

LambdaDB offers two plans:

* **Free**: includes up to **1 PB read usage**, **2 GB write usage**, **2 GB storage usage**, and **500K LIU inference usage** per month at **no cost**. After a Free plan limit is reached, additional usage is **restricted**.
* **Standard**: usage is billed based on actual measured **read usage**, **write usage**, **storage usage**, and **inference usage** as described below.

## Read usage

Read usage is billed at **\$5 per read PB** (petabyte) of measured usage.

The following requests contribute to read usage based on **collection size**:

* **Collection query** ([document query](/reference/api/endpoint/document-query))
* **Document fetch** ([document fetch](/reference/api/endpoint/document-fetch))
* **Document list** ([document list](/reference/api/endpoint/document-list))

For these operations, the size of the collection is reflected in read usage.

**Per-request minimum:** each request is counted as at least **1 GB** of read usage.

**Strong consistency:** for **query** and **fetch** requests, if you set `consistentRead` to `true`, an **additional 1 GB** is added to read usage for that request (on top of the per-request minimum and the collection-size basis). See also [Search overview](/guides/search/search-overview) and [Fetch data](/guides/documents/fetch-data).

## Write usage

Write usage is billed at **\$1 per write GB** of measured usage.

**Upsert**, **update**, and **bulk-upsert** ([document upsert](/reference/api/endpoint/document-upsert), [document update](/reference/api/endpoint/document-update), [document bulk upsert](/reference/api/endpoint/document-bulk-upsert)) are measured from the **size in bytes of the document payload** you send in the request body.

**Update** ([document update](/reference/api/endpoint/document-update)) only: each request always runs an internal **document fetch** with strong consistency (equivalent to **fetch** with `consistentRead` set to `true`). That work is billed as **read usage** under [Read usage](#read-usage)—including collection-size basis, the per-request minimum, and the **Strong consistency** rule.

**Per-request minimum** for upsert, update, and bulk-upsert: **50 KB**.

**Delete** ([document delete](/reference/api/endpoint/document-delete)): **100 KB** of write usage is added **per delete request** (fixed amount).

## Storage usage

Storage is billed on **physical storage** at **\$0.33 per GB-month**.

If you use **branching**, logical storage and physical storage can differ; billing follows **physical** storage.

Usage is computed from **hourly averages** of stored data. Those averages are summed into **GB-hours** over the billing period (not a single end-of-month snapshot).

## Inference usage

Inference usage applies when LambdaDB calls a managed model provider on your behalf, such as managed embedding generation during document writes or `knn.queryText` searches on managed embedding fields.

Inference usage is measured in **LIU** (LambdaDB Inference Unit) and billed at **\$1.05 per 1M LIU**.

LambdaDB converts provider/model token usage into LIU using LambdaDB's internal rate card. For example, different embedding models can have different LIU-per-token conversion rates. Usage is aggregated over the billing period before it is converted to the integer LIU quantity used for billing.

Current managed embedding rates:

| Provider | Model                    | Input LIU per token | Output LIU per token | Approx. cost per 1M input tokens |
| :------- | :----------------------- | ------------------: | -------------------: | -------------------------------: |
| `openai` | `text-embedding-3-small` |                0.02 |                    0 |                          \$0.021 |
| `openai` | `text-embedding-3-large` |                0.13 |                    0 |                         \$0.1365 |
| `openai` | `text-embedding-ada-002` |                 0.1 |                    0 |                          \$0.105 |

If the aggregated LIU value is positive but less than 1, it is rounded up to **1 LIU** so non-zero managed model usage is not dropped.

See also [Managed embeddings](/guides/collections/managed-embeddings).

## Billing cycle

On the **first day of each calendar month**, usage for the **previous month**—read, write, storage, and inference—is aggregated and invoiced for the **Standard** plan.