2.0× less energy than GPT-4o Mini.
GPT-4o Mini Environmental Impact
Lightweight version of GPT-4o for cost-efficient tasks
The figures below are for one quick question. A longer chat with follow-ups uses about 0.14 Wh, and an hour or two of agent work about 4.0 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
13% of a Google search.
14% of a Google search.
About 2.8× a drop of water and 3% 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~7,143 queries to fill 1 litre
Where GPT-4o Mini sits
#13 of 199 by energy per query. Lighter than 94% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
1.5× less energy than GPT-4o 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
- 4.3 Wh
- Carbon
- 1.8 g
- Water
- 15 mL
A month of 5 chats a day, 5 days a week. The energy is 36% of a phone charge.
Work out your own →- Energy
- 17.3 Wh
- Carbon
- 7.4 g
- Water
- 61 mL
A month of 20 chats a day, 5 days a week. The energy is about 1.4× a phone charge and 16% of a kettle boil.
Work out your own →- Energy
- 86.6 Wh
- Carbon
- 36.8 g
- Water
- 303 mL
A month of 100 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 →How does GPT-4o Mini compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate GPT-4o Mini at ~0.04 Wh for a quick single question. No independent estimate on the current basis covers GPT-4o mini, so we place it between the two mini-class models CLEER does cover — GPT-4.1 mini (~0.034 Wh) and GPT-5 mini (~0.05 Wh). This is our extrapolation, not a CLEER figure or a measurement. It replaces our earlier ~0.14 Wh estimate, which was built on 2025 benchmark figures for older hardware.
Power source & carbon
Runs on the same Microsoft Azure infrastructure as other OpenAI models (US East Virginia and Sweden Central). Its lower compute requirements mean shorter GPU engagement times per query, reducing the effective energy draw despite running on the same hardware.
Water use
At ~0.14 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 GPT-4o Mini
GPT-4o Mini is the proof that smaller can be smarter — at least when it comes to the planet. It delivers roughly 90% of GPT-4o's capability while using roughly a tenth of the energy per query, making it the single most impactful choice an everyday ChatGPT user can make to reduce their AI footprint. OpenAI designed it as a distilled version of GPT-4o, trained to match the larger model's behaviour at a fraction of the inference cost. For the vast majority of tasks — drafting emails, answering questions, summarising articles — the quality difference is imperceptible, but the energy difference is not.
These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for GPT-4o Mini. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
GPT-4o Mini in context
Key insights
- Uses less than a third of the average energy for text and chat models
The OpenAI GPT family
One chart per tier, on a shared time axis. Hover a dot for details; click to open that version.
Newer in this tier: GPT-5.4 Mini uses 0.03 Wh per query, 20% less than GPT-4o Mini.
Show 3 more tiers
32 versions across 8 tiers. Lightest: GPT-OSS 20B (0.02 Wh); heaviest: GPT Image 2 (5.0 Wh). Charts share a time axis but each tier has its own energy scale, so its trend is clear; the percentage is the change from a tier’s first version to its latest.
What does your GPT-4o Mini usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use GPT-4o Mini.
Frequently asked questions
How much energy does GPT-4o Mini use per query?
Each GPT-4o Mini query consumes approximately 0.04 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).
What is GPT-4o Mini's carbon footprint?
Based on the carbon intensity of Azure US East / Sweden, each query produces approximately 0.02 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 GPT-4o Mini use?
Each query consumes approximately 0.14 mL of water, primarily used for cooling the data centers that process the request.
How does GPT-4o Mini compare to a Google search?
A GPT-4o Mini query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while GPT-4o Mini uses 0.04 Wh.
Technical details
- Architecture
- Transformer (decoder-only, distilled)
- Context window
- 128,000 tokens
- Release date
- 2024-07-18
- Open source
- No