Backup Storage Prices

Checked

Meter

A retrieval tier is a speed option, not a storage class

A retrieval tier is a speed option for making archive data readable. It sits inside a storage class's recovery workflow and can change latency, retrieval price, and restore-request price without changing where the source object is stored.

Put your own numbers through the calculator to see what this meter does to a normal month and to the day you restore.

A retrieval tier chooses recovery speed inside an archive workflow

A retrieval tier is a named speed option for making archive data readable. The selected option can change the expected delay, price per retrieved byte, and price per restore request. [3] [4] [5]

A retrieval tier is not a storage class. The object remains in its selected class, while the retrieval tier describes how one recovery request is processed. A provider that publishes one retrieval rate with no speed choice has a retrieval meter but no named retrieval-tier choice in the captured data. [3] [1]

A retrieval tier chooses recovery speed inside an archive workflow
TermWhat it selectsWhat can changeSource ref
Storage classThe object's ongoing storage and access contract [2]Storage, retrieval, requests, duration, overhead, and restore workflow[2] [4]
Retrieval tierThe speed mode for one archive recovery request [3]Latency, retrieval bytes, and restore-request price[3] [4]
Retrieval latencyThe published time range before data becomes readable [3]Recovery-time eligibility[3]
EgressThe later network path to the recovery destination [4]Destination-aware transfer cost, separate from retrieval[4]

Amazon S3 and Azure publish named speed choices in the captured dataset

Only Amazon S3 and Azure Blob Storage publish multiple named retrieval-speed options in the 61 captured offers. The table copies the rates, requests, regions, and latency wording from providers.json and its official source pages; it does not recompute them. [1] [6] [7] [8]

A numeric zero copied from a published tier is rendered as not charged. Missing latency remains not published, and one named option is not presented as a multi-option choice. [1]

Amazon S3 and Azure publish named speed choices in the captured dataset9 rows
Amazon S3 and Azure publish named speed choices in the captured dataset
Provider and classRetrieval tierRetrieved-byte treatmentRestore-request treatmentPublished latencySource ref
Amazon S3 Glacier Flexible Retrieval, us-east-1Expedited$0.03/GB [6]$10.00 per 1,000 [6]1 to 5 minutes [3][6] [3]
Amazon S3 Glacier Flexible Retrieval, us-east-1Standard$0.01/GB [6]$0.05 per 1,000 [6]3 to 5 hours [3][6] [3]
Amazon S3 Glacier Flexible Retrieval, us-east-1Bulknot charged [6]not charged [6]5 to 12 hours [3][6] [3]
Amazon S3 Glacier Deep Archive, us-east-1Standard$0.02/GB [6]$0.10 per 1,000 [6]Within 12 hours [3][6] [3]
Amazon S3 Glacier Deep Archive, us-east-1Bulk$0.0025/GB [6]$0.025 per 1,000 [6]Within 48 hours [3][6] [3]
Azure Blob Archive LRS, East USStandard rehydration$0.02/GB [7]$0.50 per 1,000 [7]Up to 15 hours for objects under 10 GB [5][7] [5]
Azure Blob Archive LRS, East USHigh-priority rehydration$0.10/GB [7]$5.00 per 1,000 [7]May complete in less than 1 hour for objects under 10 GB [5][7] [5]
Azure Blob Archive LRS, West EuropeStandard rehydration$0.024/GB [8]$0.60 per 1,000 [8]Up to 15 hours for objects under 10 GB [5][8] [5]
Azure Blob Archive LRS, West EuropeHigh-priority rehydration$0.13/GB [8]$6.50 per 1,000 [8]May complete in less than 1 hour for objects under 10 GB [5][8] [5]

Most vendors publish a single retrieval rule or no named speed tier

The groups below are class-scoped and can overlap for a provider with several classes. They preserve the difference between a named speed choice, one paid retrieval rule, an allowance with an unpublished overage, a not charged rule, and missing archive details. [1]

A read-only restore can add retrieval, restore and read requests, temporary-copy storage, and egress. It never triggers early deletion. [16] [4]

Most vendors publish a single retrieval rule or no named speed tier
Captured retrieval shapeProviders or classesState treatmentSource ref
Multiple named speed choicesAmazon S3 Glacier Flexible Retrieval and Deep Archive; Azure Blob Archive [1]Use the selected tier's byte, request, and latency fields[1]
Single paid retrieval rule with no named speed choiceGoogle Nearline, Coldline, and Archive; R2 Infrequent Access; Scaleway Glacier; OVHcloud Infrequent Access and Active Archive; Oracle Infrequent Access; Tigris Infrequent Access and Archive Instant Retrieval [1]A retrieval meter exists, but retrieval-tier latency is not published unless separately sourced[1]
Allowance with priced excessDigitalOcean Spaces Cold Storage [9]$0.01/GiB after the monthly 1x average-daily-storage allowance; recovery latency remains not published[1] [9] [10]
Archive retrieval details incompleteOVHcloud Cold Archive; Vultr Archive [11] [12]not published; do not name a cheapest or fastest option[11] [12]
No paid retrieval tier in the captured primary offerBackblaze B2; Wasabi; IDrive e2; Hetzner; Akamai; captured Storj Standard; Filebase; Telnyx [1]not charged for the captured retrieval meter where stated, not a claim about every future class[1]
Cloudflare R2 recovery boundaryInfrequent Access retrieval is $0.01/GB while internet egress is not charged; Class A and Class B operations remain billed [13]A zero egress line does not erase retrieval or requests[13]
Wasabi recovery boundaryRetrieval is not charged in the captured offer, while excess egress pricing is not published beyond the fair-use policy [1] [14]Stop at not published rather than turn excess into $0[1] [14]
Backblaze B2 recovery boundaryRetrieval is not charged; egress is free up to 3 times average monthly storage, then $0.01/GB [1] [15]Apply the published allowance before the overage[1] [15]

Sources

Every figure above comes from one of these pages, on the date shown. Each numbered reference in the text links to its entry here. Vendors change prices; if a date looks old, check the source. Three vendors publish a machine-readable feed and the rest are re-checked by hand, which is why the dates are not uniform.

The source ledger16 sources
  1. 1This repository: providers.jsonrepository · checked 2026-07-25T15:34:44Z
  2. 2AWS documentation: Storage class introdocs.aws.amazon.com · checked 2026-07-26
  3. 3AWS documentation: Restoring objects retrieval optionsdocs.aws.amazon.com · checked 2026-07-26
  4. 4Amazon Web Services: S3 pricingaws.amazon.com · checked 2026-07-26
  5. 5Microsoft Learn: Archive rehydrate overviewlearn.microsoft.com · checked 2026-07-26
  6. 6AWS Price List API: Us east 1pricing.us-east-1.amazonaws.com · checked 2026-07-25T15:34:44Z
  7. 7Azure Retail Prices API: Retail pricesprices.azure.com · checked 2026-07-25T15:34:44Z
  8. 8Azure Retail Prices API: Retail pricesprices.azure.com · checked 2026-07-25T15:34:44Z
  9. 9DigitalOcean: Spaces object storagewww.digitalocean.com · checked 2026-07-26
  10. 10DigitalOcean documentation: Pricingdocs.digitalocean.com · checked 2026-07-26
  11. 11OVHcloud: Cold archivewww.ovhcloud.com · checked 2026-07-25T15:34:44Z
  12. 12Vultr documentation: Limitsdocs.vultr.com · checked 2026-07-26
  13. 13Cloudflare developer docs: R2 pricingdevelopers.cloudflare.com · checked 2026-07-25T15:34:44Z
  14. 14Wasabi: Faqwasabi.com · checked 2026-07-25T15:34:44Z
  15. 15Backblaze: Transaction pricingwww.backblaze.com · checked 2026-07-25T15:34:44Z
  16. 16AWS documentation: Restoring objectsdocs.aws.amazon.com · checked 2026-07-26