Usesconvention · the cacheLevel 2 of 6 machine operationMachine operation, level 2 of 6Used to calculate 5 entries, level 3Calculated with 2 entries, levels 1 and 2Database structure 
6Territories
5Organisations
4Occupations and activities
3Uses
1Calculation factorsRe-read 1,000 tokens from the cache
The context that an agent re-reads at each step (instructions, files, previous exchanges) is largely served from the server's cache.
- The calculation covers the computation needed to serve the context again from the cache.
- Out of scope: data centre cooling, counted separately, and server manufacturing.
Sentence to citeRe-read 1,000 tokens from cache: 0.015 gCO2e per 1,000 tokens, for 0.032 Wh of electricity, servers worldwide (458 gCO2e/kWh).
- Calculated with
- Used to calculate
How the calculation is built
No provider publishes this cost: the database counts a token re-read for one tenth of a token read (convention C4).
Comparison with the other machine operations
Characteristics
| Unit | 1,000 tokens : 0.1 share of the cost of a token read |
|---|---|
| Default location | world, 458 gCO2e/kWh (Ember 2025, life cycle); 11 other locations to choose from |
| Counted | the computation needed to serve the context again from the cache |
| Not counted | data centre cooling, counted separately, and server manufacturing |
| Status | convention |
All the characteristics
| Identifier | IA-0012, projetcelsius.com/en/ai/database/IA-0012/ |
|---|---|
| Version | 0.3 of 2 November 2026 |
| Category | Machine operations, what the server computes |
| Choice of the selected value | database calculation from the entries this one is made of, at the quantities of the unit |
| Sources | calculation of the database |
| Licence | CC BY 4.0 |
Usage parameters
Advanced settings
Result for the chosen case
a token re-read from cache at 10% of a token read, servers worldwide: 0.015 gCO2e, 0.032 Wh.
Breakdown by item
Quantity, unit value, contribution and nature of the data for each item
| Item | Quantity | Unit value | Contribution | Share | Nature of the data |
|---|---|---|---|---|---|
| Read 1,000 tokens | × 0.1 | 0.32 Wh | 0.032 Wh | 100 % | convention |
Entries that use it (5)
Conversation of 10 exchanges, Deep research, Voice mode, 1 minute, Coding agent hour, Browser agent
Sources of the calculation
2 publications, for this entry and those used to calculate it, with the chosen parameters.
The result is calculated by Projet Celsius. The sources below support its uses, its factors and its conversion; they do not all measure this total.
Energy and factors
The references of the selected values and of the entries used in this calculation.
Watershed · Aug. 2026
Estimating GHG Emissions from AI Use: Framework for Corporate-Level Measurement ↗ (new tab)
Role and limits : Watershed
Author. Bistline, Ulissi, Davis, Glidden, Joyce, Li, Mohsenin and Suh (Watershed)
What the publication covers. factors per 1,000 tokens read and written at the server before PUE (host and standby machines included), PUE separate (1.10 for a large operator, 1.56 for an unknown operator)
What it does not cover. clean measurements, the model and the hardware
Reading by the database. Default factors proposed for review (public data as of June 2026); for a large operator, taken from Google's measurement published in 2025 (Elsworth et al.), which already contains the data centre overhead; constant per token, they underestimate long contexts and agents according to the authors
Reference for the variant "Medium model, Watershed default factor"
Scope of the figure used. Default factor for 1,000 tokens read, medium model, large operator, at the server before PUE (Watershed table 2, public data as of June 2026)
Limit. A default value that Watershed derives from Google's measurement (0.24 Wh for the median text query of the Gemini app), with about 500 tokens per query and a written token costing 3 times a read token; Watershed does not give the split between read and written tokens. The 0.24 Wh already include the overhead of Google's data centre (0.02 Wh, 8%): with 375 tokens read and 125 written, the simplest reading, the factor contains it, and the PUE of 1.10 applied afterwards counts it a second time (about 9%). Values proposed for review, final at the next version of the framework
Conversion into carbon
The source of the electricity factor of the selected location.
Worldwide: 458 gCO2e/kWh, life cycle.
Role and limits : Ember
Author. Ember, Our World in Data
What the publication covers. electricity generation over the life cycle, by country
What it does not cover. guarantees of origin
Reading by the database. The same source for all countries
Conversion of electricity into carbon: worldwide
Scope of the figure used. the production of electricity over the life cycle, including power plant construction and fuels
Limit. An average for the chosen country, not the electricity contract or the data centre of a specific service.
Nature of the data
Published readings, conventions, assumptions
- database conventions 100 %
Calculation assumptions
Quantities, nature and source of each assumption
Read 1,000 tokens : × 0.1
Convention C4: a token re-read from cache costs 10% of a token read
Methodology conventions
With their alternatives
| The cache | A token re-read from the cache costs 10% of a token read |
|---|---|
| The default location | Without other information, the servers are in the world, at the world average electricity |
| Electricity, location-based, on a life cycle basis | The kilowatt-hour is that of the servers' country, on a life cycle basis, from a single source for all countries |
| Two significant figures | A calculated value is rounded to two significant figures, a published value is reproduced with the precision of its source; the calculation keeps full precision |
| The formula | the sum of what makes up the entry, then CO2e: electricity (Wh) multiplied by the carbon intensity of the server location (gCO2e/kWh), divided by 1,000 |
| Calculate a case without an entry | The formula, the default values and a step-by-step example |
History
Entry in version 0.3 of 2 November 2026, in the database in version 0.4
- 2 November 2026Status : order of magnitude becomes convention.The cost of a token re-read from cache is convention C4.
- 2 November 2026Designation : 1,000 tokens re-read from cache becomes Re-read 1,000 tokens from cache.In people's own words.
- 2 November 2026Short title : Tokens in cache becomes Re-read from cache.In people's own words.
- 2 November 2026Address : tokens-relus-en-cache becomes relire-1-000-tokens-en-cache.Address in people's own words; the old one redirected.
- 31 October 2026Creation of the database, in its first version (0.1).
