2.0× less energy than Cursor.
Cursor Environmental Impact
AI-native code editor — most popular AI coding tool
One query, in context
Energy, carbon and water for a single use. One code edit / chat turn
About 1.4× a minute of laptop use and 10% of a phone charge.
About 4.2× a Google search and 24% of 10 m by car.
About 90× a drop of water and 90% of a teaspoon of water.
- Where it runsMulti-cloud (Azure, AWS)
- Grid carbon intensity450 g CO₂/kWh · 25% renewable
- Compared with a Google search4x more than a search (0.3 Wh)
- Water~222 queries to fill 1 litre
Where Cursor sits
#142 of 199 by energy per query. Heavier than 70% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
2.7× less energy than Cursor.
6.0× less energy than Cursor.
What a month of use adds up to
Pick how much you use it. Based on one quick use at a time, five days a week.
- Energy
- 259.8 Wh
- Carbon
- 108.3 g
- Water
- 974 mL
A month of 10 requests a day, 5 days a week. The energy is about 2.4× a kettle boil and 4% of a UK home's day.
Work out your own →- Energy
- 1.04 kWh
- Carbon
- 433.0 g
- Water
- 3.90 L
A month of 40 requests a day, 5 days a week. The energy is about 9.4× a kettle boil and 14% of a UK home's day.
Work out your own →- Energy
- 5.20 kWh
- Carbon
- 2.17 kg
- Water
- 19.48 L
A month of 200 requests a day, 5 days a week. The energy is about 47× a kettle boil and 70% of a UK home's day.
Work out your own →How does Cursor compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
Cursor is the most popular AI coding tool, using a mix of models (GPT-4, Claude, custom fine-tunes) depending on the task. A typical code edit or chat turn consumes ~1.2 Wh, though Tab autocomplete uses lighter models (~0.1 Wh). Heavy users may trigger 100+ queries per hour, making Cursor one of the highest-volume AI use cases per user.
Power source & carbon
Cursor routes queries to multiple model providers (OpenAI, Anthropic, custom), inheriting the carbon profile of each. Infrastructure spans Azure and AWS.
Water use
At ~4.5 mL per code edit. The aggregate water impact is significant given the frequency of use — a developer using Cursor for 8 hours may trigger hundreds of model calls.
About Cursor
Cursor is a code assistant model from Anysphere, released in March 12, 2024. AI-native code editor — most popular AI coding tool. Each query uses 1.2 Wh of energy and produces 0.50 g of CO₂. That's about 4.0x what a Google search consumes.
These figures are estimates derived from hardware specifications and API benchmarks — Anysphere has not published official energy data for Cursor. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
Cursor in context
What does your Cursor usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use Cursor.
Frequently asked questions
How much energy does Cursor use per query?
Each Cursor query consumes approximately 1.2 Wh of energy. This is 4x more than a traditional Google search (~0.3 Wh).
What is Cursor's carbon footprint?
Based on the carbon intensity of Multi-cloud (Azure, AWS), each query produces approximately 0.50 g of CO2. The grid in this region has a carbon intensity of 450 g CO2/kWh with 25% renewable energy.
How much water does Cursor use?
Each query consumes approximately 5 mL of water, primarily used for cooling the data centers that process the request.
How does Cursor compare to a Google search?
A Cursor query uses 4x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Cursor uses 1.2 Wh.
Technical details
- Architecture
- Multi-model (GPT-4, Claude, custom)
- Release date
- 2024-03-12
- Open source
- No