Obtenir une suggestion de code

Name: Get a code suggestion
Creator: Projet Celsius
License: https://creativecommons.org/licenses/by/4.0/

Projet Celsius

Database entryUsesLevel 3 of 6 useUse, level 3 of 6Used to calculate 3 entries, level 4Calculated with 4 entries, levels 1 and 2Database structure

Get a code suggestion

The few lines that a coding assistant suggests while you type, from a small model that reads about 6,000 characters around the cursor. Projet Celsius estimate.

"Read 1,000 tokens" accounts for 76% of emissions in this scenario.
100% of the calculation rests on database assumptions; it does not measure actual use.
Out of scope: server manufacturing, model training, the network and the user's device.

Compare

Calculated with

Used to calculate

Breakdown of emissions by item

0.031 gCO2e in total: 0.069 Wh of electricity × 458 gCO2e/kWh (servers worldwide).

Inputs of the calculation 3

PUE of the data centre, Read 1,000 tokens, Write 1,000 tokens

Annual emissions from getting a code suggestion, by frequency

Your frequencyPeriod

Read the values at100 times a year

Reading: at 14,000 uses per year, "Code suggestion" weighs as much as charging a phone once a week. Carbon footprint (CO2e) over one year, by number of uses. Each use is a straight line; "Code suggestion" is highlighted, with the chosen parameters, and compared with 5 reference uses at their default settings; the solid line is one phone charge per week over a year, and the point where the task reaches it. Servers worldwide. Calculation from the Projet Celsius AI Impact Database.

How the calculation is built

A developer receives hundreds of them per day.

Comparison with the other uses

The topic "Code and agents"

Code suggestion0.031 gCO2e
Automated workflow0.11 gCO2e, 3.5 times the value of "Code suggestion"
Generate a function0.54 gCO2e, 17 times the value of "Code suggestion"
Have code reviewed0.59 gCO2e, 19 times the value of "Code suggestion"

↓ The heaviest use in the topic, "Coding agent hour": 310 gCO2e, 9,800 times more

Emissions of one use, linear scale, 4 of the 6 uses in the topic, those of the same order of magnitude (at most 25 times between the smallest and the largest value). For calculated values, servers worldwide.

Characteristics

Unit	1 suggestion
Default location	world, 458 gCO2e/kWh (Ember 2025, life cycle); 11 other locations to choose from
Counted	the model reading and writing tokens, and data centre cooling
Not counted	server manufacturing, model training, the network and the user's device
Status	estimated, 1 other published value

All the characteristics identifier, version, rule for the value, sources, licence

Identifier	IA-0217, projetcelsius.com/en/ai/database/IA-0217/
Version	0.1 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

Emissions by server location

Emissions associated with electricity (CO2e)

Poland0.04 gCO2e
World0.031 gCO2e
United States0.026 gCO2e
European Union0.014 gCO2e
France0.0028 gCO2e

× 14 between Poland and France, for the same electricity

Ember 2025, over the life cycle. The same use consumes 0.069 Wh in each location.

Get a code suggestion · result per suggestion · estimated · one server location per row.Included: the model reading and writing tokens, and data centre cooling. Out of scope: server manufacturing, model training, the network and the user's deviceFind this case: projetcelsius.com/en/ai/database/tasks/get-a-code-suggestion/Projet Celsius calculation, AI Impact Database, version 0.4 of 13 November 2026 · IA-0217, entry in version 0.1 · engine 0.3.1 · CC BY 4.0.

Usage parameters

Advanced settings model class, calibration

Model classCalibration

Result for the chosen case

Location of the servers

For a carbon footprint

The row for a carbon footprint

Item	purchases of services (GHG Protocol scope 3, category 1); regulatory BEGES, category 4
Quantity	1 suggestion
Factor	0.031 gCO2e per suggestion, IA-0217 version 0.1, based on the grid at the location (location-based), servers worldwide
Total	0.031 gCO2e · not counted: server manufacturing, model training, the network and the user's device

Breakdown of emissions by item

Emissions associated with electricity (CO2e)

Read 1,000 tokens0.024 gCO2e · 76 %
Write 1,000 tokens0.0046 gCO2e · 15 %
PUE of the data centre0.0029 gCO2e · 9.1 %

Get a code suggestion · result per suggestion · estimated · servers worldwide.Included: the model reading and writing tokens, and data centre cooling. Out of scope: server manufacturing, model training, the network and the user's deviceFind this case: projetcelsius.com/en/ai/database/tasks/get-a-code-suggestion/Projet Celsius calculation, AI Impact Database, version 0.4 of 13 November 2026 · IA-0217, entry in version 0.1 · engine 0.3.1 · CC BY 4.0.

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 (small model, about 8 billion parameters)	× 0.983 after calibration, 1.5 before	0.053 Wh	0.052 Wh	76 %	assumption · GitHub
Write 1,000 tokens (small model, about 8 billion parameters)	× 0.0629 after calibration, 0.096 before	0.16 Wh	0.01 Wh	15 %	assumption
PUE of the data centre	× 1.10 on the rest		0.0062 Wh	9 %	convention

Entries that use it (3)

Developer, 1 year, Data scientist, 1 year, GitHub Copilot, 1 year

Sources of the calculation

5 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.

GitHub · May 2023
How GitHub Copilot is getting better at understanding your code ↗ (new tab)
Read 1,000 tokens
Role and limits : GitHub
What the publication covers. about 6,000 characters of code read for a suggestion
What it does not cover. electricity
Reading by the database. A post of 2023, updated in 2024: the current size is not published
- Code suggestion → : Read 1,000 tokens →
  The code around the cursor, about 6,000 characters or 125 lines, read by a small model
  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.
Projet Celsius · November 2026
Tokens per word, per line of code and per cell, measured with 7 public tokenisers
Read 1,000 tokens · Write 1,000 tokens
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
- Code suggestion → : Read 1,000 tokens →
  Length convention: a line of code
  Scope of the figure used. From 10 tokens per line (Python standard library) to 19 (the TypeScript code of this site), measured with GPT-4o tokenisation
  Limit. This publication supports the quantity of text or content processed, not its carbon footprint.
- Code suggestion → : Write 1,000 tokens →
  Length convention: a line of code
  Scope of the figure used. From 10 tokens per line (Python standard library) to 19 (the TypeScript code of this site), measured with GPT-4o tokenisation
  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.

ML.ENERGY · February 2026
The ML.ENERGY Leaderboard v3, data by task ↗ (new tab)
Read 1,000 tokens · Write 1,000 tokens
Role and limits : ML.ENERGY
Author. Chung et al., University of Michigan
What the publication covers. GPU energy per token, per response, per image, in steady state, according to the number of requests served at once
What it does not cover. processors, host memory, data centre cooling, manufacturing
Reading by the database. The best open benchmark: it serves to compare model sizes with each other, not as a production value
- Read 1,000 tokens →
  Support for the "Small model" setting
  Scope of the figure used. A model of about 8 billion active parameters, like Llama 3.1 8B: about 6 times less electricity per token than the medium model, according to the ML.ENERGY benchmark.
  Limit. The setting is a convention of the database supported by this publication.
- Write 1,000 tokens →
  Reference of the variant "Small model, about 8 billion parameters"
  Scope of the figure used. Llama 3.1 8B, one H100 GPU, 64 requests at a time, GPU only, per 1,000 tokens written, reading of the question included
  Limit. GPU only, on a benchmark: the database keeps only the ratio to the 70 billion model, 1 to 6.7
  The measurement covers a different scope; it is not a direct measurement of this entry.
Watershed · Aug. 2026
Estimating GHG Emissions from AI Use: Framework for Corporate-Level Measurement ↗ (new tab)
Read 1,000 tokens · Write 1,000 tokens · Data centre PUE
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
- Read 1,000 tokens →
  Reference factor: 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. This measurement concerns the reference variant, not a measurement of "Small model, about 8 billion parameters". 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. The 0.24 Wh already include the overhead of Google's data centre (0.02 Wh, 8%): with 375 tokens read and 125 written, on 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, to be finalised in the next version of the framework
- Write 1,000 tokens →
  Reference factor: 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. This measurement concerns the reference variant, not a measurement of "Small model, about 8 billion parameters". 3 times the read factor, based on the write-to-read ratio adopted by Watershed (Patel et al., Splitwise, 2024). Same derivation and same caveat as for reading: Google's 0.24 Wh already include about 8% for the data centre. Values proposed for review, to be finalised in the next version of the framework
- Code suggestion → : 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.
- Data centre PUE →
  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.

Ember · 2026
Global Electricity Review 2026, and Our World in Data based on Ember ↗ (new tab)
Grid electricity
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
- Grid electricity →
  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.

Green: same scope as the selected value (measured in dark, estimated or published in light). Grey: other scope. Empty circle: check by the database or discarded figure. Logarithmic scale.

Source	Date	Electricity	What the figure measures	Scope	Status
Code suggestionselected by the database, v0.1	2026	0.0687 Wh	the value selected by the database	same scope	estimated
ML.ENERGY, benchmark v3 ↗The ML.ENERGY Leaderboard v3, données par tâche	Feb. 2026	0.0243 Wh	Qwen 3 Coder 30B, of which 3 billion active, code completion in the middle of a file, 255 tokens written on average, one H100 GPU, 64 queries at a time, GPU only · GPU only, on a test bench	other scope	measured

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

What this figure rests on

Projet Celsius assumptions 100 %

A share counts as an assumption as soon as a quantity set by Projet Celsius (a frequency, a share done with AI, a headcount) enters its calculation, even if the rest rests on published measurements.

Calculation assumptions

Quantities, nature and source of each assumption

Read 1,000 tokens : × 0.983
The code around the cursor, about 6,000 characters or 125 lines, read by a small model
assumption · GitHub · Read 1,000 tokens
Write 1,000 tokens : × 0.0629
The suggestion, about 8 lines, written by a small model
assumption · Write 1,000 tokens

Methodology conventions

With their alternatives

The full methodology

The data centre	Server electricity is multiplied by 1.10 for the data centre · alternatives: × 1.72 from chips to the full service at Google, never to be combined
The default location	Without other information, the servers are in the world, at the world average electricity · alternatives: the United States, where most of the large assistants run
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 · alternatives: market-based, with purchase contracts, shown alongside when published
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

The changelog

2 November 2026Version 0.1 of the entry, as of the date of its current value.
31 October 2026Creation of the database, in its first version (0.1).

Citation

Projet Celsius, AI Impact Database, version 0.4 of 13 November 2026, "Get a code suggestion", IA-0217 (entry in version 0.1 of 2 November 2026), projetcelsius.com/en/ai/database/IA-0217/ · CC BY 4.0.

Download

JSON Markdown