Why a million small objects cost more than the same bytes in one file

A size floor and metadata overhead are different charges

A minimum billable object size replaces the charged size when an object is below a class threshold. S3 Standard-IA, One Zone-IA, and Glacier Instant Retrieval bill objects smaller than 128 KB as 128 KB. S3 Glacier Flexible Retrieval and Deep Archive instead add 40 KB of metadata to every archived object. [1]

AWS splits that 40 KB into 8 KB billed at S3 Standard rates and 32 KB billed at the archive-class rate. AWS counts storage in binary units: 1 GB is 2^30 bytes and 1 KB is 1,024 bytes, so a GB holds 1,048,576 KB. One million archived objects therefore add 40,000,000 KB, or 38.15 GB, of metadata, even when their logical payload already totals 1,000 GB. [1] [2]

Units differ between vendors. AWS's GB and KB are binary, the same sizes as GiB and KiB, and DigitalOcean and Telnyx write GiB and KiB. This guide keeps each vendor's own unit and says so whenever a figure is converted. [1] [3] [4]

The same 1,000 GB can carry $0.99 or $216.67 of Deep Archive storage

The worked workload holds logical payload at 1,000 GB for one full month in S3 Glacier Deep Archive in us-east-1. Average object size divides the payload evenly, sizes follow AWS's binary units (1 GB = 1,048,576 KB and 1 MB = 1,024 KB), and replication, versioning, requests, retrieval, temporary copies, and egress are excluded from this storage-only table. [2] [1]

The payload line is always 1,000 GB x $0.00099 = $0.99. Object size changes only the object count and the two metadata lines. At a 1 MB average there are 1,024,000 objects, so the backup carries 39.06 GB of pure metadata and costs $1.20 after rounding. [2] [1]

Below 9.80 KB, Deep Archive is more expensive than S3 Standard

For this 1,000 GB us-east-1 comparison, S3 Standard costs 1,000 x $0.023 = $23.00 in the first storage band and has no minimum billable object size. Deep Archive costs $0.99 for payload plus $215.68 divided by average object size in KB for its split metadata. [2] [1]

Setting $0.99 + $215.68 / size equal to $23.00 gives a crossover at 9.799 KB, rounded to 9.80 KB, or about 10,034 bytes. Below that average, the nominally cheapest class is the more expensive of these two storage tiers. This is a storage-only crossover, not a restore winner, because retrieval, requests, temporary-copy storage, and egress remain separate. [2] [1]

A read-only restore exposes the request cost of small objects

This restore keeps the archived source unchanged and restores the same 1,000 GB to the public internet using Deep Archive Standard retrieval. It assumes one RestoreObject request and one GET per object, the full 100 GB AWS internet-transfer allowance remains, and the temporary S3 Standard copy is kept for 7 days in an illustrative 30-day month. [2] [1] [6]

The byte-based subtotal is constant: $20.00 retrieval, $81.00 egress, and $5.37 temporary-copy storage, or $106.37 after rounding. Object count changes the request subtotal at $0.10 per 1,000 Standard restore requests plus $0.0004 per 1,000 GET requests. Real tools can issue additional HEAD, LIST, range, and retry operations, so the one-restore-plus-one-GET assumption is a lower-bound estimate rather than a universal request count. [2] [1]

Early deletion does not apply and contributes $0.00. A read-only restore can charge retrieval, restore and GET requests, temporary-copy storage, and egress, but it does not delete, overwrite, move, or transition the archived source. [1] [6]

Egress and requests decide the restore, not the storage-rate headline

A storage-only crossover answers which tier holds the bytes more cheaply. It does not answer which provider restores them more cheaply. Backblaze B2, Cloudflare R2, and Wasabi apply three different restore rules: a proportional egress allowance with a published overage, no internet-egress charge with paid operations, and no egress fee under a fair-use guideline. [7] [9] [10]

The examples below use 1,000 GB of monthly average or active storage as the provider rule requires. They keep egress and request lines separate, and they do not add early-deletion charges because every restore remains read-only. [7] [9] [10] [6]

Small-file rules at all 18 vendors

Our price table covers 66 offers from 18 vendors. A positive floor appears only where the vendor publishes one. Where the vendor states no rule, the floor is not published, which is not the same as zero; where the vendor says there is no floor, we mark it as not applicable. Class-specific rules stay class-specific. [1] [11] [12]

Amazon S3, DigitalOcean Cold, Hetzner, Storj, Telnyx, and Wasabi have a positive billable-size rule in our price table. Amazon also adds 40 KB of archive metadata per object. Backblaze, Akamai, Filebase, Cloudflare R2, and Google Cloud Storage state that there is no positive floor. For the remaining seven vendors the floor is not published. [1] [3] [10] [8] [20] [25] [26] [27]

Look-alike rules and two floors now settled

The rates, and whether each is published, come from our price table. The DigitalOcean Cold mismatch was resolved on 2026-07-29, so the prices we checked now include the documented 128 KiB storage and read floors. Wasabi's 4 KB floor is settled too: its pricing FAQ bills objects smaller than 4 KB as 4 KB, and our price table uses the same floor. [10] [3]

Upload eligibility, tiering eligibility, and recommended object size do not count as a billable-size rule. They can affect whether an upload or tiering action is supported, but they do not prove how stored bytes are billed. [14] [1] [17]