Image Generation

GPT Image 1.5 Environmental Impact

Q: What is GPT Image 1.5's carbon footprint?

Based on the carbon intensity of its inference location (Azure / Multi-cloud), each GPT Image 1.5 query produces approximately 1.66g of CO2.

Q: How does GPT Image 1.5 compare to a Google search?

A GPT Image 1.5 query uses 13x more than a traditional Google search in terms of energy consumption. A Google search uses approximately 0.3 Wh, while GPT Image 1.5 uses 3.8 Wh per query.

Q: How much water does GPT Image 1.5 use?

Each GPT Image 1.5 query consumes approximately 13.7 mL of water, primarily used for cooling the data centers that process the request.

HeavyEstimated

Replaced DALL-E 3 as default — 4x faster, improved photorealism

Architecture: Native multimodal image generation
Provider: OpenAI

3.8 Wh

Energy per query

1.7 g

CO₂ per query

14 mL

Water per query

13x more than

vs Google search

Energy per query

3.8 Wh

13x more than a Google search (0.3 Wh)

CO2 per query

1.7 g

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

Water per query

14 mL

~73 queries to fill 1 litre

Processing location

Azure / Multi-cloud

Provider

OpenAI

How does GPT Image 1.5 compare?

Ranked #105 of 152 models by energy per query

View full comparison

Detailed Breakdown

Energy Consumption

GPT Image 1.5 replaced DALL-E 3 as OpenAI's default image generation model. At ~3.8 Wh per image, it is 20% cheaper and 4x faster than GPT Image 1 while producing significantly improved photorealism. It leads the LM Arena image Elo at 1,264. DALL-E 2 and 3 are being deprecated in May 2026.

OpenAI — GPT Image 1.5 (Dec 2025)

Power Source & Carbon

Runs on OpenAI's multi-cloud infrastructure. The 4x speed improvement suggests more efficient hardware utilisation per image.

OpenAI — Image Generation API

Water Usage

At ~13.7 mL per image, comparable to DALL-E 3 despite improved quality.

UC Riverside — Making AI Less Thirsty (2023)

About GPT Image 1.5

GPT Image 1.5 is a image generation model from OpenAI, released in December 16, 2025. Replaced DALL-E 3 as default — 4x faster, improved photorealism. Each query uses 3.8 Wh of energy and produces 1.7 g of CO₂. That's 13x the energy of a Google search — reflecting the computational demands of image generation.

These figures are estimates derived from hardware specifications and API benchmarks — OpenAI has not published official energy data for GPT Image 1.5. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

GPT Image 1.5 in Context

34.7 kWh

per year

Your yearly GPT Image 1.5 footprint

At 25 queries per day, your annual GPT Image 1.5 usage consumes 34.7 kWh — roughly what a fridge uses in a month. That produces 15.1 kg of CO₂.

13x

vs a text query

Image vs text: the energy gap

Generating one image with GPT Image 1.5 uses 13x more energy than a text conversation with ChatGPT. The diffusion process that creates images requires many iterative passes through the model, each refining the image from noise — far more compute per output than generating text one token at a time.

OpenAI GPT Family

How energy efficiency has evolved across versions.

GPT-4 Turbo2024-04-09

0.50 Wh

GPT-4o2024-05-13

0.43 Wh

GPT-4o Mini2024-07-18

0.14 Wh

GPT-4.52025-02-27

20.5 Wh

GPT-4o Image Generation2025-03-25

4.5 Wh

GPT-4.1 Nano2025-04-14

0.27 Wh

GPT-4.12025-04-14

0.45 Wh

GPT-4.1 Mini2025-04-14

GPT-OSS 120B2025-08-07

1.8 Wh

GPT-OSS 20B2025-08-07

0.35 Wh

GPT-5.22025-12-11

5.0 Wh

GPT Image 1.5Current2025-12-16

3.8 Wh

GPT-5.2 Codex2026-01-14

4.0 Wh

GPT-5.3 Codex2026-02-05

4.5 Wh

GPT-5.42026-03-05

5.5 Wh

GPT-5.4 Mini2026-03-05

1.0 Wh

GPT-5.4 Nano2026-03-05

0.30 Wh

What does your GPT Image 1.5 usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use GPT Image 1.5.

Calculate My Compute

Frequently Asked Questions

How much energy does GPT Image 1.5 use per query?

Each GPT Image 1.5 query consumes approximately 3.8 Wh of energy. This is 13x more than a traditional Google search (~0.3 Wh).

What is GPT Image 1.5's carbon footprint?

Based on the carbon intensity of Azure / Multi-cloud, each query produces approximately 1.7 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 Image 1.5 use?

Each query consumes approximately 14 mL of water, primarily used for cooling the data centers that process the request.

How does GPT Image 1.5 compare to a Google search?

A GPT Image 1.5 query uses 13x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while GPT Image 1.5 uses 3.8 Wh.