Storage price trends - live cost per terabyte history

678 priced listings across 4 categories, tracked daily since 2026-08-04 · last updated 2026-10-18

Quick answer

We snapshot every tracked listing once a day and keep it. These pages plot those snapshots: median and cheapest cost per terabyte for hard drives, SSDs and LTO tape, and per gigabyte for server RAM, with new and recertified stock drawn as separate lines. Every window longer than the history we hold prints a dash instead of a number. Pick a category below, or see the storage crisis tracker for all of them on one index.

Hard drives →

Enterprise SATA and SAS nearline drives, new and recertified, priced per terabyte.

$14.99/TB

Median

$34.39/TB

30 days

+2.0%

224+ matched pairs

90 days

—

All-time low

$11.63/TB

2026-08-04

SSDs →

Datacenter NVMe and SAS solid-state drives, new and pulled, priced per terabyte.

$119.99/TB

Median

$215.00/TB

30 days

-6.1%

17+ matched pairs

90 days

—

All-time low

$76.30/TB

2026-08-04

Server RAM →

Registered ECC DDR4 and DDR5 modules, priced per gigabyte.

$4.92/GB

Median

$12.06/GB

30 days

+3.3%

37+ matched pairs

90 days

—

All-time low

$4.31/GB

2026-08-04

LTO tape →

LTO-7, LTO-8 and LTO-9 media, priced per terabyte of native capacity.

$4.89/TB

Median

$6.42/TB

30 days

+1.0%

6+ matched pairs

90 days

—

All-time low

$4.89/TB

2026-08-04

Corrected October 1, 2026

Corrected October 5, 2026: every series now starts on August 4, 2026. Before that date our recorded prices rarely changed - about 2% of listings on a given day, against about 12% on every day since - and on August 4, 2026 itself 218 of 621 listings changed at once. That is a change in how prices were recorded, not in the market, so nothing before it is compared with anything after it. One listing whose product changed under the same Amazon listing is also excluded from before August 4, 2026. Until November 2, 2026 there are fewer than 90 days of comparable history, so 90-day figures are withheld rather than shortened. What the published 90-day figures were, against the same index measured from August 4, 2026, series ending 4 October 2026:

Hard drives: 90 days +8.71% as published; +3.83% since August 4, 2026 (at least 150 matched listings per day).
SSDs: 90 days +19.46% as published; -5.25% since August 4, 2026 (at least 17 matched listings per day).
Server RAM: 90 days -3.32% as published; +15.13% since August 4, 2026 (at least 37 matched listings per day).
LTO tape: 90 days +3.71% as published; +3.87% since August 4, 2026 (at least 6 matched listings per day).

The earlier corrections below are kept as they were published.

The percentages on this page come from our matched-model index, which compares each listing only with its own earlier price. Until October 1, 2026 it also counted days when a listing was out of stock. Amazon keeps quoting a price for a listing nobody can buy, and those quotes moved. A price you cannot buy at is not a price, so a listing now counts only when it was in stock on both days being compared. A listing that drops out leaves the comparison rather than being filtered from one side, which is the same rule our recertified-versus-new figure uses.

Measured on the correction date, the same data both ways:

Hard drives: 30 days +0.97% became -0.10% (at least 365 then 228 matched listings per day); 90 days +15.41% became +12.87% (at least 159 then 159).
SSDs: 30 days -0.60% became -2.03% (at least 67 then 21 matched listings per day); 90 days +22.60% became +20.10% (at least 46 then 21).
Server RAM: 30 days +8.43% became +8.77% (at least 50 then 37 matched listings per day); 90 days -4.38% became -3.31% (at least 7 then 7).
LTO tape: 30 days +4.18% became +2.77% (at least 7 then 6 matched listings per day); 90 days +6.59% became +3.27% (at least 7 then 6).

34% of hard drives pairs since stock was first recorded left the index. The dropped quotes skew dear, not cheap: an out-of-stock listing's quoted price ran 2.02% above the same listing's in-stock price, across 591 comparisons, so the correction is not removing cheap prices to flatter the index.

57% of ssds pairs since stock was first recorded left the index. The dropped quotes skew dear, not cheap: an out-of-stock listing's quoted price ran 3.25% above the same listing's in-stock price, across 66 comparisons, so the correction is not removing cheap prices to flatter the index.

17% of server ram pairs since stock was first recorded left the index. The dropped quotes skew CHEAP: an out-of-stock listing's quoted price ran 1.15% below the same listing's in-stock price, across 47 comparisons. That is the survivorship risk - if cheaper listings are the ones that sell out, an index of what stays in stock leans dear - so we print it rather than ask you to trust us.

11% of lto tape pairs since stock was first recorded left the index. Which way the dropped quotes leaned rests on only 4 same-listing comparisons (-5.61% against the in-stock price), too few to call.

A second correction, the same day. The corrected 90-day figures above were measured before three further fixes. Five listings were removed from every average we compute: three LTO-9 tape cartridges catalogued as SSDs (in stock from 23 March to 16 August), a hard-drive listing whose part number, title and capacity described three different products (in stock to 12 August), and an IronWolf Pro 2TB offered at about ten times its class median (5 to 17 August). Nine external USB and Thunderbolt drives that we had filed as internal drives were moved out of the internal averages. And for 31 drives whose capacity we had recorded wrongly and later corrected, the per-terabyte history was recomputed at the right capacity - each correction had put a one-day step into the index. Every 30-day window starts after those dates, so only the 90-day figures move. Re-measured on the same end date:

Hard drives: 90 days +12.87% became +9.76% (at least 150 matched listings per day).
SSDs: 90 days +20.10% became +21.67% (at least 17 matched listings per day).

The re-measurement also reflects listing titles read since the first correction was measured: a title that says renewed or recertified keeps that listing out of the new-condition figures. Hard drives, step by step: +12.87% as published, +9.61% without the five listings, +9.55% without the external drives, +9.76% with capacities recomputed.

Stock was not recorded before August 8, 2026, so earlier days are counted as before - we cannot tell which of those prices were buyable. The live figures elsewhere on this page use the corrected rule and will move on from the values above as new days arrive.

These pages measure the market; they do not list it. The drives behind the hard drive trend are listed live, cheapest per terabyte first, on SATA hard drives and SAS hard drives, and beside the outlook on the cheapest HDD right now.

Why a price tracker keeps its history

Most price comparison sites show you today and throw yesterday away. That makes them useful for one question, what is cheapest right now, and useless for the question people actually ask during a shortage, which is whether the number in front of them is normal.

A price is only meaningful against a baseline. $18 per terabyte means nothing on its own; it means a great deal if the category has been sitting at $26, and it means the market has moved past you if it has been at $14 all quarter. Everything on these pages exists to supply that baseline from observations rather than from memory or vibes.

The honest limitation is stated on every page: we started keeping snapshots on a specific date, and comparisons that need more history than that print a dash. There is a strong temptation to stretch a few months into a year-over-year headline, and that temptation is exactly how confident-sounding wrong numbers enter circulation. The window grows on its own. Until it does, the pages say what they can support.

Everything here is free to cite, screenshot and embed with a link. If you need a cut we do not publish, ask.

Share:WhatsApp Facebook Post on X

Methodologysource, cadence and window since 2026-08-04show

Source. Our own tracking of Amazon US listings through the Amazon Creators API. One retailer, stated plainly, rather than an unnamed blend.
Cadence. Prices refresh about once a day. One snapshot per listing per day is written to the price history, and these charts plot those daily snapshots.
Window. Tracking for this category begins 2026-08-04 and runs to 2026-10-18. Comparisons longer than that window print a dash rather than a number.
Cost per tb. Listed item price divided by the manufacturer's stated capacity. Shipping and tax are not included. Server RAM is quoted per gigabyte; storage per terabyte.
Levels. The cheapest and median figures are plain observations across every listing we priced that day in that category and condition. They tell you where the market sits.
Changes. Every percentage change is a chained matched-model (Jevons) index, not a comparison of two days' medians. Each daily step compares only listings we priced on both that day and the day before, taking the geometric mean of their individual price relatives, so a product entering or leaving the catalogue cannot move it. Comparing medians across dates would measure catalogue churn as if it were price movement, and on this dataset that difference has been large enough to invert the story.
Condition. New and recertified are separate series throughout. Refurbished enterprise stock is frequently the cheapest per terabyte, and blending it into one line would hide both that fact and any change in its supply.
Coverage. 678 priced listings in this category on the most recent day. Out-of-stock listings keep their last observed price in the history and are labelled where they appear in tables.
What we do not do. No modelled projections, no smoothing, no imputed values for days we did not observe. A gap in a line is a gap in the data.

Citing this page

Quote a figure, link to the page, and tell readers where the number came from. That is ordinary citation and it needs no permission from us.

We do not offer this as an open dataset, and we removed an earlier notice that did. The underlying prices are retrieved under a licence that does not permit us to pass redistribution rights on to anyone else, so bulk reuse, republication of the series, or building a product on top of these numbers is something to ask about first rather than something we can grant in a footer. The contact page reaches us, and we would rather have the conversation than have you rely on a permission we cannot give.

DatacenterDisk. “Storage Price Trends - Live $/TB History.” DatacenterDisk, 2026. https://datacenterdisk.com/trends

Storage crisis tracker →

One index, every category

Cheapest per TB now →

The live ranking

What is a good $/TB? →

The benchmark explained

Where prices go next →

What the trend implies

Where to buy →

Every channel we track

Recertified drives →

The cheap end, explained