2.9× less energy than o4-mini.
o4-mini Environmental Impact
OpenAI's latest compact reasoning model with tool use
The figures below are for one quick question. A longer chat with follow-ups uses about 0.70 Wh, and an hour or two of agent work about 20.0 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
67% of a Google search.
73% of a Google search.
About 14× a drop of water and 14% of a teaspoon of water.
- Where it runsAzure US East / Sweden
- Grid carbon intensity450 g CO₂/kWh · 25% renewable
- Compared with a Google searchabout the same as a search (0.3 Wh)
- Water~1,389 queries to fill 1 litre
Where o4-mini sits
#53 of 199 by energy per query. Lighter than 75% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
3.3× less energy than o4-mini.
10× less energy than o4-mini.
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
- 21.7 Wh
- Carbon
- 9.4 g
- Water
- 78 mL
A month of 5 chats a day, 5 days a week. The energy is about 1.8× a phone charge and 20% of a kettle boil.
Work out your own →- Energy
- 86.6 Wh
- Carbon
- 37.7 g
- Water
- 312 mL
A month of 20 chats a day, 5 days a week. The energy is about 7.2× a phone charge and 79% of a kettle boil.
Work out your own →- Energy
- 433.0 Wh
- Carbon
- 188.4 g
- Water
- 1.56 L
A month of 100 chats a day, 5 days a week. The energy is about 3.9× a kettle boil and 6% of a UK home's day.
Work out your own →How does o4-mini compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate o4-mini at ~0.2 Wh for a quick single question. o4-mini is a small reasoning-only model: it reasons before every answer, so we start from the standard-chat figure for its model class (GPT-4.1 mini / GPT-5 mini, ~0.04 Wh on the CLEER basis (Sustainable AI Group, Sept 2026: full-facility energy for one quick question on current hardware)) and multiply by 5. That multiplier sits between the roughly 2x measured for medium reasoning effort and the 13x the Joule 2026 production study found for long reasoning-style responses; a quick question does not trigger the longest chains, but a hard problem can cost ten times more again. This is our extrapolation, not a CLEER figure or a measurement. It replaces our earlier ~1.5 Wh estimate, which was built on 2025 benchmark figures for older hardware.
Power source & carbon
Runs on Microsoft Azure and multi-cloud infrastructure. OpenAI expanded to AWS and Google Cloud in 2025, potentially allowing greener region placement.
Water use
At ~0.72 mL per quick question, derived from the energy estimate at the ~3.6 L/kWh water factor we apply to this model's infrastructure. Water scales directly with energy, so longer chats, reasoning and agentic sessions use proportionally more.
About o4-mini
o4-mini is a text and chat model from OpenAI, released in April 16, 2025. OpenAI's latest compact reasoning model with tool use. Each query uses 0.20 Wh of energy and produces 0.09 g of CO₂. That's roughly comparable to a traditional Google search.
These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for o4-mini. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
o4-mini in context
What does your o4-mini usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use o4-mini.
Frequently asked questions
How much energy does o4-mini use per query?
Each o4-mini query consumes approximately 0.20 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).
What is o4-mini's carbon footprint?
Based on the carbon intensity of Azure US East / Sweden, each query produces approximately 0.09 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 o4-mini use?
Each query consumes approximately 0.72 mL of water, primarily used for cooling the data centers that process the request.
How does o4-mini compare to a Google search?
A o4-mini query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while o4-mini uses 0.20 Wh.
Technical details
- Architecture
- Transformer with adaptive chain-of-thought and tool use
- Context window
- 200,000 tokens
- Release date
- 2025-04-16
- Open source
- No
- Training data cutoff
- 2025-03