UsesLevel 3 of 6 useUse, level 3 of 6Used to calculate 22 entries, levels 3 and 4Calculated with 4 entries, levels 1 and 2Database structure 
6Territories
5Organisations
4Occupations and activities
2Machine operations
1Calculation factorsQuery a 30-page PDF
A question about an attached document of 30 pages. Projet Celsius estimate.
- "Read 1,000 tokens" accounts for 86% of emissions in this scenario.
- The calculation covers reading the document, the response and cooling of the data centre.
- Out of scope: server manufacturing, model training, the network and the user's device.
Sentence to citeQuerying a 30-page PDF, Projet Celsius estimate: 2.2 gCO2e per question, for 4.7 Wh of electricity, servers worldwide (458 gCO2e/kWh).
Breakdown of emissions by item
2.2 gCO2e in total: 4.7 Wh of electricity × 458 gCO2e/kWh (servers worldwide).
Inputs of the calculation
PUE of the data centre, Read 1,000 tokens, Write, with reasoning
How the calculation is built
The model first reads the 19,200 tokens of the document, then responds. Beyond 2 pages, reading costs more than the response.
Comparison with the other uses
↓ The heaviest use in the topic, "Deep research": 45 gCO2e, 21 times more
Emissions of one use, linear scale, 7 of the 21 uses in the topic. For calculated values, servers worldwide.
Characteristics
| Unit | 1 question |
|---|---|
| Default location | world, 458 gCO2e/kWh (Ember 2025, life cycle); 11 other locations to choose from |
| Counted | reading the document, the response and cooling of the data centre |
| Not counted | server manufacturing, model training, the network and the user's device |
| Status | estimated, 1 other published value |
All the characteristics
| Identifier | IA-0043, projetcelsius.com/en/ai/database/IA-0043/ |
|---|---|
| Version | 0.3 of 2 November 2026 |
| Category | Uses, a request to AI |
| 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
For a carbon footprint
| Item | purchases of services (GHG Protocol scope 3, category 1); regulatory BEGES, category 4 |
|---|---|
| Quantity | 1 question |
| Factor | 2.2 gCO2e per question, IA-0043 version 0.3, based on the local grid (location-based), servers worldwide |
| Total | 2.2 gCO2e · not counted: server manufacturing, model training, the network and the user's device |
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 | × 12.7 | 0.32 Wh | 4 Wh | 86 % | convention |
| Write, with reasoning (without reasoning) | × 0.262 | 0.96 Wh | 0.25 Wh | 5 % | convention |
| PUE of the data centre | × 1.10 on the rest | 0.43 Wh | 9 % | convention |
Entries that use it (22)
Handle a customer request, Book written with AI, End-to-end study, Accountant, 1 year, Human resources, 1 year, Journalist, 1 year, Consultant, 1 year, Lawyer, 1 year, Researcher, 1 year, Developer, 1 year, Data scientist, 1 year, Field-based occupation, 1 year, Student, 1 year, Free personal use, 1 year, ChatGPT Plus, 1 year, ChatGPT Pro, 1 year, Claude Pro, 1 year, Claude Max, 1 year, Google AI Pro, 1 year, Vibe Pro, 1 year, Perplexity Pro, 1 year, ChatGPT Business, 1 year and
Sources of the calculation
3 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.
Uses and assumptions
These publications shed light on AI tasks and uses. They do not measure the carbon footprint of the case calculated.
Projet Celsius · November 2026
Tokens per word, per line of code and per cell, measured with 7 public tokenisers
Role and limits : Projet Celsius
What the publication covers. 479,888 words from 196 blog articles and their English translation, code from the site and the Python library, a table of measurements; tokenisers of GPT-4o, GPT-4, Llama 3, Gemini (via Gemma 3), Mistral, DeepSeek and Qwen
What it does not cover. the Claude tokeniser, not public
Reading by the database. A measurement on technical texts, figures included; to be repeated if publishers change their tokeniser
Projet Celsius measurement, repeated on request with the public tokenisers
Query a PDF → : Read 1,000 tokens →
Length convention: one page
Scope of the figure used. A report page, headings and paragraphs included: between the 1,500-character sheet (250 words) and a full A4 page in single spacing (about 550 words, at 6.1 characters per word measured on our articles)
Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
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
Reference for the variant "Medium model, Watershed default factor"
Scope of the figure used. Default factor for 1,000 tokens written, medium model, large operator, at the server before PUE (Watershed table 2, public data as of June 2026)
Limit. 3 times the reading factor, based on the ratio between writing and reading selected by Watershed (Patel et al., Splitwise, 2024). Same derivation and same caveat as for reading: Google's 0.24 Wh already include about 8% of data centre. Values proposed for review, final at the next version of the framework
Query a PDF → : Data centre PUE →
The data centre, convention C3
Scope of the figure used. building cooling and losses
Limit. This figure covers part of the calculation; it does not measure the whole entry.
Reference of the selected value
Scope of the figure used. Default factor for a large operator, from the server to the data centre; 1.56 for an unknown operator
Limit. A default value, not a measurement
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.
Published values
1 figure for the same operation, each within its own scope.
| Source | Date | Electricity | What the figure measures | Scope | Status |
|---|---|---|---|---|---|
| Query a PDFselected by the database, v0.3 | 2026 | 4.73 Wh | the value selected by the database | same scope | estimated |
| Epoch AI ↗How much energy does ChatGPT use? | Feb. 2025 | 40 Wh | GPT-4o, a document of about 200 pages (100,000 tokens read) and a response of 500 tokens | other scope | estimated |
The published figures do not all count the same scope; the scope of each figure is written next to it. Why do the estimates diverge?
Nature of the data
Published readings, conventions, assumptions
- database conventions 100 %
Calculation assumptions
Quantities, nature and source of each assumption
Read 1,000 tokens : × 12.7
The document, 30 pages by default, and the question
Write, with reasoning : × 0.262
The response (convention C1)
Methodology conventions
With their alternatives
| The standard query | A query counts 100 tokens read and 400 written |
|---|---|
| The data centre | Server electricity is multiplied by 1.10 for the data centre |
| 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 |
Uses in the hub
Charts, figures, analyses and articles that cite this entry
History
Entry in version 0.3 of 2 November 2026, in the database in version 0.4
- 2 November 2026Designation : A question with an attached document becomes Query with attached document (30 pages).More precise designation: the object first, the specification after the comma, the quantity or period at the end; the former title remains searchable.
- 2 November 2026Designation : Query with attached document (30 pages) becomes Query a 30-page PDF.The name in people's own words.
- 2 November 2026Short title : Query with document becomes Query a PDF.In people's own words.
- 2 November 2026Address : requete-avec-document-joint becomes interroger-un-pdf-de-30-pages.The old address redirected.
- 2 November 2026Functional unit : 1 query becomes 1 question.In people's own words.
- 31 October 2026Creation of the database, in its first version (0.1).
