Text / Chat

o3-mini Environmental Impact

StandardEstimated

Cost-efficient reasoning model with adjustable thinking effort

Architecture
Transformer with adaptive chain-of-thought
Context
200,000 tokens
Provider
OpenAI
2.0 Wh
Energy per query
0.90 g
CO₂ per query
8 mL
Water per query
7x more than
vs Google search

Energy per query

2.0 Wh

7x more than a Google search (0.3 Wh)

CO2 per query

0.90 g

US East (Virginia) grid (450 gCO₂/kWh)

Water per query

8 mL

~125 queries to fill 1 litre

Processing location

Azure US East / Sweden

Provider

OpenAI

Category

Text / Chat

Grid carbon intensity

450 g CO2/kWh (25% renewable)

How does o3-mini compare?

Ranked #86 of 152 models by energy per query

0 Wh0.5 Wh1 Wh1.5 Wh2 WhLLaMA 3.2 1BGemini 1.5 ProGPT-4.1 Nanoo3-miniGoogle search (0.3 Wh)

Detailed Breakdown

Energy Consumption

o3-mini offers adjustable reasoning effort (low/medium/high), allowing users to trade quality for efficiency. At medium effort, we estimate ~2 Wh per query — significantly more efficient than o1-mini while often matching its reasoning quality. High effort can use 3-5x more.

Power Source & Carbon

Runs on Microsoft Azure infrastructure. The adaptive effort feature means energy consumption varies significantly based on task difficulty settings.

Water Usage

At ~8 mL per query (medium effort), o3-mini is more water-efficient than its predecessors. Low-effort queries use proportionally less.

About o3-mini

o3-mini is a text and chat model from OpenAI, released in January 31, 2025. Cost-efficient reasoning model with adjustable thinking effort. Each query uses 2.0 Wh of energy and produces 0.90 g of CO₂. That's 7x the energy of a Google search — reflecting the computational demands of text and chat.

These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for o3-mini. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

o3-mini in Context

200 MWh
estimated daily

At global scale

With an estimated 10M+ daily users averaging 10 queries each, o3-mini consumes roughly 200 MWh of electricity per day — enough to power 6667 homes.

18.3 kWh
per year

Your yearly o3-mini footprint

At 25 queries per day, your annual o3-mini usage consumes 18.3 kWh — roughly what a fridge uses in a month. That produces 8.2 kg of CO₂.

OpenAI o3 Family

What does your o3-mini usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use o3-mini.

Calculate My Compute

Frequently Asked Questions

How much energy does o3-mini use per query?

Each o3-mini query consumes approximately 2.0 Wh of energy. This is 7x more than a traditional Google search (~0.3 Wh).

What is o3-mini's carbon footprint?

Based on the carbon intensity of Azure US East / Sweden, each query produces approximately 0.90 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 o3-mini use?

Each query consumes approximately 8 mL of water, primarily used for cooling the data centers that process the request.

How does o3-mini compare to a Google search?

A o3-mini query uses 7x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while o3-mini uses 2.0 Wh.

Technical Details

Architecture

Transformer with adaptive chain-of-thought

Context window

200,000 tokens

Release date

2025-01-31

Open source

No

Training data cutoff

2024-10