o3 (Reasoning) Environmental Impact

Energy Consumption

The o3 reasoning model consumes approximately 21.4 Wh per query — about 71x more energy than a Google search. Reasoning models perform multiple internal inference passes ("chain-of-thought" steps) before producing a final answer, which multiplies GPU compute time significantly compared to standard chat models.

Power Source & Carbon

Runs on Microsoft Azure's infrastructure, primarily in the US East region. The Virginia data center corridor, where many Azure facilities are concentrated, has a carbon intensity of approximately 450 g CO2/kWh — significantly above the US average of 380 g CO2/kWh — due to reliance on natural gas and remaining coal generation.

Water Usage

With ~100 mL per query, o3 consumes roughly as much water as a small glass of water for each interaction. This high water usage is a direct consequence of the extended GPU runtime required for multi-step reasoning.

How much energy does o3 (Reasoning) use per query?

Each o3 (Reasoning) query consumes approximately 21.4 Wh of energy. This is 71x more than a traditional Google search (~0.3 Wh).

What is o3 (Reasoning)'s carbon footprint?

Based on the carbon intensity of Azure US East / Sweden, each query produces approximately 10.0 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 (Reasoning) use?

Each query consumes approximately 100 mL of water, primarily used for cooling the data centers that process the request.

How does o3 (Reasoning) compare to a Google search?

A o3 (Reasoning) query uses 71x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while o3 (Reasoning) uses 21.4 Wh.

Architecture

Transformer with chain-of-thought reasoning (decoder-only)

Context window

200,000 tokens

Release date

2025-01-31

Open source

No

Training data cutoff

2024-10