2.5× less energy than GPT-5 Mini.
GPT-5 Mini Environmental Impact
Compact GPT-5 variant for cost-sensitive applications
The figures below are for one quick question. A longer chat with follow-ups uses about 0.18 Wh, and an hour or two of agent work about 5.0 Wh.
One query, in context
Energy, carbon and water for a single use. Quick single question (one exchange)
17% of a Google search.
18% of a Google search.
About 3.6× a drop of water and 4% of a teaspoon of water.
- Where it runsAzure / Multi-cloud
- Grid carbon intensity450 g CO₂/kWh · 25% renewable
- Compared with a Google searchabout the same as a search (0.3 Wh)
- Water~5,556 queries to fill 1 litre
Where GPT-5 Mini sits
#17 of 199 by energy per query. Lighter than 92% of all models. Lit dots are the same kind of model; click any dot to open it.
Want something lighter?
1.6× less energy than GPT-5 Mini.
1.9× less energy than GPT-5 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
- 5.4 Wh
- Carbon
- 2.4 g
- Water
- 19 mL
A month of 5 chats a day, 5 days a week. The energy is 45% of a phone charge.
Work out your own →- Energy
- 21.7 Wh
- Carbon
- 9.5 g
- Water
- 78 mL
A month of 20 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
- 108.3 Wh
- Carbon
- 47.6 g
- Water
- 390 mL
A month of 100 chats a day, 5 days a week. The energy is about 9.0× a phone charge and 98% of a kettle boil.
Work out your own →How does GPT-5 Mini compare?
Next to similar models. Bars use a log scale, so each step is a big jump.
Detailed breakdown
Energy
We estimate GPT-5 mini at ~0.05 Wh for a quick single question, taken from the CLEER dataset (Sustainable AI Group, Sept 2026). The figure covers the full facility — accelerators, host servers, idle capacity and cooling. CLEER cannot measure closed models directly: it projects per-token energy from open models it has benchmarked, on B200/B300-class accelerators (proxy-match confidence 0.679 on a 0-1 scale). On the same basis a typical multi-turn chat comes to ~0.18 Wh and a typical agentic coding session to ~4 Wh, so how the model is used matters far more than which prompt you send. This replaces our earlier ~0.8 Wh estimate, which was extrapolated from 2025 benchmark figures on older hardware. OpenAI has published no per-query figures for this model.
Power source & carbon
Same multi-cloud infrastructure as GPT-5. The smaller model size allows more efficient GPU utilisation.
Water use
At ~0.18 mL per quick question, derived from the energy estimate at the ~3.6 L/kWh water factor we apply to this provider's infrastructure. Water scales directly with energy, so longer chats and agentic sessions use proportionally more.
About GPT-5 Mini
GPT-5 Mini is a text and chat model from OpenAI, released in August 7, 2025. Compact GPT-5 variant for cost-sensitive applications. Each query uses 0.05 Wh of energy and produces 0.02 g of CO₂. That's roughly comparable to a traditional Google search. It ranks in the top quartile of text and chat models for energy efficiency (#16 of 135).
These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for GPT-5 Mini. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.
GPT-5 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, 36% less than GPT-5 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-5 Mini usage cost the planet?
Use the calculator to estimate your personal footprint based on how often you use GPT-5 Mini.
Frequently asked questions
How much energy does GPT-5 Mini use per query?
Each GPT-5 Mini query consumes approximately 0.05 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).
What is GPT-5 Mini's carbon footprint?
Based on the carbon intensity of Azure / Multi-cloud, 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-5 Mini use?
Each query consumes approximately 0.18 mL of water, primarily used for cooling the data centers that process the request.
How does GPT-5 Mini compare to a Google search?
A GPT-5 Mini query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while GPT-5 Mini uses 0.05 Wh.
Technical details
- Architecture
- Multimodal Transformer (distilled)
- Context window
- 256,000 tokens
- Release date
- 2025-08-07
- Open source
- No
- Training data cutoff
- 2025-06