UsesLevel 4 of 6 occupation or activityOccupation or activity, level 4 of 6Calculated with 2 entries, levels 1 and 4Database structure 
6Territories
5Organisations
3Uses
2Machine operations
1Calculation factorsAgents talking to each other, 1 months
The same month of work handed to several agents that share the tasks and talk to each other. Projet Celsius estimate.
- The calculation covers the steps of all the agents, their exchanges and the cooling of the data centre.
- 100% of the calculation rests on database assumptions; it does not measure actual use.
- Out of scope: server manufacturing and model training.
Sentence to citeAgents talking to each other, 1 month, Projet Celsius estimate: 210 kgCO2e per month, for 470 kWh of electricity, servers worldwide (458 gCO2e/kWh).
- Calculated with
Breakdown of emissions by item
210 kgCO2e in total: 470 kWh of electricity × 458 gCO2e/kWh (servers worldwide).
Inputs of the calculation
PUE of the data centre, Re-read from cache, Read 1,000 tokens, Write 1,000 tokens, Write, with reasoning, Coding agent hour, Web search with an AI, Browser agent
How the calculation is built
Anthropic observes about 15 times the tokens of a conversation for such a system, against 4 times for a single agent.
Comparison with other occupations and activities
Characteristics
| Unit | 1 month |
|---|---|
| Default location | world, 458 gCO2e/kWh (Ember 2025, life cycle); 11 other locations to choose from |
| Counted | the steps of all the agents, their exchanges and the cooling of the data centre |
| Not counted | server manufacturing and model training |
| Status | estimated |
All the characteristics
| Identifier | IA-0329, projetcelsius.com/en/ai/database/IA-0329/ |
|---|---|
| Version | 0.1 of 2 November 2026 |
| Category | Occupations and activities, one person, one year |
| 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
30 days, 6 agent hours a day, servers worldwide: 210 kgCO2e, 470 kWh.
For a carbon footprint
| Item | purchases of services (GHG Protocol scope 3, category 1); regulatory BEGES, category 4 |
|---|---|
| Quantity | 1 month |
| Factor | 210 kgCO2e per month, IA-0329 version 0.1, using the local grid mix (location-based), servers worldwide |
| Total | 210 kgCO2e · not counted: server manufacturing and model training |
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 |
|---|---|---|---|---|---|
| Autonomous agent, 1 month | × 3.75 | 120 kWh | 470 kWh | 100 % | assumption |
Entries that use it
No other entry in the database is calculated from this one.
Sources of the calculation
8 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.
Anthropic · June 2025
Role and limits : Anthropic
What the publication covers. ratio of the tokens of an agent and of a multi-agent system to those of a conversation
What it does not cover. electricity and the measurement method
Reading by the database. An order of magnitude drawn from the publisher's data, without a detailed method
Agents talking to each other, 1 month →
Published observation on uses
Scope of the figure used. Several agents talking to each other consume about 15 times the tokens of a conversation, a single agent about 4 times
Limit. Used as a multiplier for agents talking to each other relative to the single agent
Agents talking to each other, 1 month → : Autonomous agent, 1 month →
Several agents talking to each other use about 15 times the tokens of a conversation, a single agent about 4 times (Anthropic, 2025): the same month of work costs 15/4 times the single agent
Scope of the figure used. steps handed to the AI, data centre
Limit. The quantity and the share entrusted to AI are database assumptions, not a measured footprint.
Anthropic · 2026
Role and limits : Anthropic
What the publication covers. tokens of an image according to its size: one patch of 28 × 28 pixels per token, 1,296 for a megapixel
What it does not cover. electricity
Reading by the database. The publisher's billing rule
Analyse an image → : Read 1,000 tokens →
The photo cut into about 1,100 image tokens, read as text
Scope of the figure used. server, excluding the data centre
Limit. The quantity and the share entrusted to AI are database assumptions, not a measured footprint.
Analyse an image → : Read 1,000 tokens →
Length convention: a photo sent to an AI
Scope of the figure used. A one-megapixel photo, cut into image patches: 765 tokens at OpenAI for GPT-4o, 1,032 at Google, 1,229 for recent OpenAI models, 1,296 at Anthropic
Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
EnronSent
Role and limits : EnronSent
Author. Will Styler
What the publication covers. 96,106 messages sent by Enron employees, 13,810,266 words
What it does not cover. the messages received
Reading by the database. Professional emails from 2000 and 2001: an order of magnitude, not a norm
Automated workflow → : Read 1,000 tokens →
Length convention: an email
Scope of the figure used. A typical email: the sent messages of the Enron corpus average about 144 words; figure read in an excerpt, notice not verified
Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
Write an email → : Write, with reasoning →
The email written, 150 words
Scope of the figure used. server, excluding the data centre
Limit. The quantity and the share entrusted to AI are database assumptions, not a measured footprint.
Write an email → : Read 1,000 tokens →
Length convention: an email
Scope of the figure used. A typical email: the sent messages of the Enron corpus average about 144 words; figure read in an excerpt, notice not verified
Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
Write an email → : Write, with reasoning →
Length convention: an email
Scope of the figure used. A typical email: the sent messages of the Enron corpus average about 144 words; figure read in an excerpt, notice not verified
Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
Zhang and Nam · June 2026
HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification ↗ (new tab)
Role and limits : Zhang and Nam
Author. Yujin Zhang and Daye Nam
What the publication covers. 45 web agent trajectories: 13.16 steps and 6.02 pages visited per task on average
What it does not cover. electricity
Reading by the database. A small sample, which gives the order of magnitude of an agent's steps
Web search with an AI → : Read 1,000 tokens →
The 5 pages found, read by the model, and the question: web agents visit 6 pages per task on average
Scope of the figure used. server, excluding the data centre
Limit. The quantity and the share entrusted to AI are database assumptions, not a measured footprint.
Agent in the browser → : Analyse an image →
A screenshot read at each step, 15 steps: published web agents take 13 on average
Scope of the figure used. image reading on the server; outside the data centre
Limit. The quantity and the share entrusted to AI are database assumptions, not a measured footprint.
Energy and factors
The references of the selected values and of the entries used in this calculation.
Google · January 2009
Role and limits : Google
What the publication covers. a search, data centre
Reading by the database. Never remeasured
Reference of the selected value
Scope of the figure used. A search, data centre included
Limit. Never publicly remeasured; Google's AI answers are not published
Hausfather · Aug. 2026
Role and limits : Hausfather
Author. Zeke Hausfather, The Climate Brink
What the publication covers. intensive personal use of Claude Code, tokens recorded and converted into electricity
Reading by the database. A researcher's personal measurements, not a study
Autonomous agent, 1 month → : Coding agent hour →
The hours the agent works: 6 active hours per day over 30 days, waiting the rest of the time; the coding agent hour serves as the agent hour
Scope of the figure used. agent steps, context re-read from cache, data centre
Limit. This figure covers part of the calculation; it does not measure the whole entry.
Coding agent hour → : Re-read from cache →
The context re-read from cache at each of the 120 steps of the hour: 96,000 tokens, 96% of a call in the median published session
Scope of the figure used. server, convention C4
Limit. This figure covers part of the calculation; it does not measure the whole entry.
Coding agent hour → : Read 1,000 tokens →
The new tokens of each step (files read, command results): 3,600, 3.6% of a call
Scope of the figure used. server, excluding the data centre
Limit. This figure covers part of the calculation; it does not measure the whole entry.
Coding agent hour → : Write 1,000 tokens →
The tokens written at each step, draft included: 900 on average in the published logs
Scope of the figure used. server, excluding the data centre
Limit. This figure covers part of the calculation; it does not measure the whole entry.
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
Coding agent hour → : 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
Web search with an AI → : 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.
Agent in the browser → : 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.
Automated workflow → : 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.
Write an email → : 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.
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
- Projet Celsius assumptions 100 %
Calculation assumptions
Quantities, nature and source of each assumption
Autonomous agent, 1 month : × 3.75
Several agents talking to each other use about 15 times the tokens of a conversation, a single agent about 4 times (Anthropic, 2025): the same month of work costs 15/4 times the single agent
Published figures in support
Anthropic (2025): 15 times the tokens of a conversation
Several agents talking to each other consume about 15 times the tokens of a conversation, a single agent about 4 times
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 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 0.1 of 2 November 2026, in the database in version 0.4
- 2 November 2026Version 0.1 of the entry, as of the date of its current value.
- 12 November 2026Calculated value, servers worldwide : 140 kgCO2e becomes 210 kgCO2e.Consequence of the new value for the coding agent hour (from 440 to 670 Wh), decided on 12 November 2026; the entry's own data do not change, and its citation carries version 0.4 of the database.
- 31 October 2026Creation of the database, in its first version (0.1).
