Text / ChatLowEstimatedReleased 2024-12-26

DeepSeek-V3 Environmental Impact

Efficient MoE model with high capability

ArchitectureTransformer Mixture-of-Experts (decoder-only)Parameters671BContext128,000 tokensProviderDeepSeek

The figures below are for one quick question. A longer chat with follow-ups uses about 0.84 Wh, and an hour or two of agent work about 24.0 Wh.

One query, in context

Energy, carbon and water for a single use. Quick single question (one exchange)

Energy0.24Wh per query

80% of a Google search.

likely 0.12 Wh – 0.48 Wh
Carbon0.13g per query

About 1.1× a Google search and 6% of 10 m by car.

likely 0.07 g – 0.26 g
Water0.89mL per query

About 18× a drop of water and 18% of a teaspoon of water.

likely 0.45 mL – 2 mL
  • Where it runsChina (Hangzhou / Hainan)
  • Grid carbon intensity525 g CO₂/kWh · 33% renewable
  • Compared with a Google searchabout the same as a search (0.3 Wh)
  • Water~1,124 queries to fill 1 litre

Where DeepSeek-V3 sits

#65 of 199 by energy per query. Lighter than 68% of all models. Lit dots are the same kind of model; click any dot to open it.

Google searchKettle boilLLaMA 3.2 1B — 0.03 WhGemini 1.5 Pro — 0.45 WhGPT-4.1 Nano — 0.03 WhGPT-4o — 0.43 WhClaude 3.7 Sonnet — 0.21 WhGPT-4.5 — 1.0 Who3 (Reasoning) — 2.3 WhDeepSeek-R1 — 1.2 WhGrok 2 — 0.50 WhDALL-E 3 — 3.0 WhMidjourney — 7.5 WhStable Diffusion XL — 2.9 WhSora — 500 WhGitHub Copilot — 1.5 WhSuno — 75 WhGPT-4o Mini — 0.04 WhGemini 2.0 Flash — 0.08 WhClaude Opus 4 — 0.39 WhClaude Sonnet 4 — 0.21 WhClaude 3.5 Haiku — 0.06 WhMistral Large 2 — 1.8 WhLLaMA 3.1 70B — 0.38 WhPerplexity AI — 0.50 WhImagen 3 — 2.5 WhFlux.1 Dev — 3.8 WhVeo 2 — 350 WhGemini 2.5 Pro — 0.40 WhGemini 2.5 Flash — 0.24 WhGPT-4.1 — 0.37 WhGPT-4.1 Mini — 0.03 WhLLaMA 4 Scout — 0.11 WhLLaMA 4 Maverick — 0.11 WhQwen 3 235B — 0.16 WhGrok 3 — 0.40 WhGemma 3 27B — 0.16 WhPhi-4 — 0.09 WhCommand R+ — 0.56 WhGPT-4o Image Generation — 4.5 WhAdobe Firefly — 3.2 WhIdeogram 2.0 — 3.5 WhRunway Gen-3 Alpha — 200 WhKling — 250 WhPika — 180 WhLuma Dream Machine — 160 WhUdio — 70 Who1 — 2.3 Who1-mini — 0.20 Who3-mini — 0.20 Who4-mini — 0.20 WhGPT-4 Turbo — 0.50 WhGemini 1.5 Flash — 0.10 WhGemini Nano — 0.01 WhClaude 3 Opus — 0.56 WhClaude 3 Haiku — 0.06 WhLLaMA 3.1 8B — 0.06 WhLLaMA 3.1 405B — 2.1 WhLLaMA 3.3 70B — 0.38 WhLLaMA 3.2 11B Vision — 0.08 WhLLaMA 3.2 90B Vision — 0.49 WhMistral 7B — 0.06 WhMixtral 8x7B — 0.09 WhMixtral 8x22B — 0.22 WhMistral Small 3 — 0.14 WhCodestral — 0.80 WhAmazon Nova Pro — 0.30 WhAmazon Nova Lite — 0.06 WhAmazon Nova Micro — 0.03 WhERNIE Bot 4.0 — 0.30 WhDoubao Pro — 0.30 WhGLM-4 — 0.19 WhKimi — 0.25 WhJamba 1.5 Large — 1.0 WhStable Diffusion 3.5 — 3.2 WhLeonardo AI — 3.5 WhHaiLuo AI — 220 WhStable Video Diffusion — 150 WhCursor — 1.2 WhAmazon Q Developer — 1.0 WhClaude Code — 2.0 WhWindsurf (Codeium) — 0.80 WhReplit Agent — 1.5 WhWhisper — 0.50 WhOpenAI TTS — 0.30 WhElevenLabs — 1.5 WhNotebookLM Audio Overview — 15 WhClaude Sonnet 4.5 — 0.34 WhClaude Opus 4.5 — 0.42 WhClaude Opus 4.6 — 0.40 WhClaude Sonnet 4.6 — 0.20 WhGPT-5 — 0.44 WhGPT-5 Mini — 0.05 WhGPT-5.2 — 0.61 WhGPT-5.2 Codex — 0.61 WhGPT-5.4 — 0.60 WhGPT-5.4 Mini — 0.03 Who3-pro — 6.0 WhGPT Image 1.5 — 3.8 WhSora 2 — 600 WhGemini 3 Pro — 0.40 WhGemini 3 Flash — 0.15 WhGemini 3.1 Pro — 0.42 WhGemma 3 4B — 0.04 WhGemma 3 12B — 0.08 WhImagen 4 — 2.8 WhVeo 3 — 400 WhVeo 3.1 — 2.4 kWhGrok 4 — 0.60 WhGrok 4.1 — 0.50 WhDeepSeek-R1-0528 — 1.2 WhDeepSeek-V3.1 — 0.24 WhQwen3.5 (397B-A17B) — 0.13 WhQwen3.5 35B-A3B — 0.04 WhMistral Large 3 — 1.5 WhDevstral 2 — 0.60 WhVoxtral TTS — 0.40 WhKimi K2.5 — 0.30 WhGLM-5 — 0.22 WhDoubao 2.0 — 0.30 WhCommand A — 0.60 WhPhi-4 Mini — 0.04 WhPhi-4 Reasoning — 0.27 WhAmazon Nova 2 Pro — 0.35 WhMidjourney V7 — 8.0 WhFlux 2 Pro — 5.0 WhRunway Gen-4.5 — 250 WhKling 3.0 — 280 WhDevin — 3.0 WhElevenLabs v3 — 1.8 WhSuno v5.5 — 80 WhClaude Haiku 4.5 — 0.02 WhGPT-5.3 Codex — 0.45 WhGPT-5.4 Nano — 0.03 WhGPT-OSS 120B — 0.03 WhGPT-OSS 20B — 0.02 WhGemini 3.1 Flash Lite — 0.06 WhLyria 3 Pro — 50 WhDeepSeek-V3.2 — 0.25 WhGrok 4.20 — 0.50 WhQwen3-Coder 480B — 0.20 WhQwen 3.5 Omni — 0.20 WhNemotron 3 Super — 0.45 WhDoubao Seed 2.0 Pro — 0.35 WhSeedance 2.0 — 280 WhGLM-5.1 — 0.22 WhERNIE 5.0 — 0.35 WhMistral Small 4 — 0.40 WhPhi-4 Multimodal — 0.05 WhMidjourney V8 Alpha — 5.0 WhRecraft V4 — 3.0 WhLuma Ray 3 — 200 WhPika 2.5 — 210 WhGPT-5.5 — 0.51 WhGPT-5.5 Instant — 0.06 WhGPT-5.3 Instant — 0.05 WhGPT Image 2 — 5.0 WhClaude Opus 4.7 — 0.44 WhClaude Opus 4.8 — 0.53 WhClaude Fable 5 — 0.79 WhClaude Sonnet 5 — 0.24 WhDeepSeek-V4-Pro — 0.24 WhDeepSeek-V4-Flash — 0.10 WhNano Banana 2 — 1.5 WhQwen3.6 27B — 0.16 WhQwen3.7-Max — 0.45 WhSora 2 Pro — 2.1 kWhClaude Opus 5 — 0.46 WhClaude Fable 5.1 — 0.65 WhClaude Opus 5.5 — 0.45 WhClaude Sonnet 5.5 — 0.24 WhClaude Haiku 5.5 — 0.02 WhClaude Fable 5.2 — 0.60 WhGPT-5.6 Sol — 0.39 WhGPT-5.6 Terra — 0.16 WhGPT-5.6 Luna — 0.05 WhGPT-6 Astra — 0.90 WhGPT-6 Sol — 0.42 WhGPT-6 Luna — 0.06 WhGPT-6 Instant — 0.07 WhGPT-6.1 Sol — 0.42 WhGPT-6.1 Terra — 0.17 WhGemini 3.5 Flash — 0.24 WhGemini 3.5 Flash-Lite — 0.06 WhGemini 3.6 Flash — 0.21 WhGemini 3.7 Flash — 0.14 WhGemini 3.8 Flash — 0.15 WhGemini 4 Argon — 0.45 WhNano Banana 2.1 — 1.5 WhGrok 4.5 — 0.35 WhGrok 4.7 — 0.40 WhMuse Spark — 0.40 WhMuse Spark Open — 0.22 WhKimi K3 — 0.65 WhGLM-5.3 — 0.22 WhQwen3.8-Max — 0.55 WhDeepSeek-V4.1-Flash — 0.10 WhMistral Large 4 — 1.4 WhKling 4.0 — 300 WhSeedance 2.5 — 290 Wh0.1 Wh1 Wh10 Wh100 Wh1 kWhDeepSeek-V3

Want something lighter?

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
26.0 Wh
Carbon
14.1 g
Water
96 mL

A month of 5 chats a day, 5 days a week. The energy is about 2.2× a phone charge and 24% of a kettle boil.

Work out your own →
Energy
103.9 Wh
Carbon
56.3 g
Water
385 mL

A month of 20 chats a day, 5 days a week. The energy is about 8.7× a phone charge and 94% of a kettle boil.

Work out your own →
Energy
519.6 Wh
Carbon
281.4 g
Water
1.93 L

A month of 100 chats a day, 5 days a week. The energy is about 4.7× a kettle boil and 7% of a UK home's day.

Work out your own →

How does DeepSeek-V3 compare?

Next to similar models. Bars use a log scale, so each step is a big jump.

DeepSeek-V30.24 Wh
GPT-5.20.61 Wh

Detailed breakdown

Energy

CLEER (Sustainable AI Group, Sept 2026) benchmarked DeepSeek V3's open weights directly on four H200 accelerators and measured ~0.24 Wh for a quick single question and ~0.77 Wh for a typical multi-turn chat, including host servers, idle capacity and cooling. We previously showed 2.0 Wh, the Jegham et al. (2025) figure for a medium prompt, which modelled DeepSeek's own less efficient, lightly batched hosting. Notably CLEER's agentic estimate for V3 is high (~85 Wh per session) because the model is verbose in tool-use loops.

Power source & carbon

DeepSeek-V3 runs on infrastructure in mainland China, sharing facilities with DeepSeek-R1 in Hangzhou and Hainan. We apply China's 2025 grid carbon intensity of approximately 525 g CO2/kWh (Ember Global Electricity Review 2026, down from ~550) — roughly 37% higher than the US average — with coal still the single largest source. The CO2 figure (~0.13 g) is derived as 0.24 Wh × 525 gCO2/kWh.

Water use

At ~0.89 mL per quick question, derived from the energy estimate at the ~3.7 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 DeepSeek-V3

DeepSeek-V3 is an open-source text and chat model from DeepSeek, released in December 26, 2024, that runs below the category average for energy consumption at 0.24 Wh per query. Because its weights are publicly available, it can be self-hosted on any infrastructure — meaning its carbon footprint depends entirely on where and how you choose to run it. At 671B parameters, it efficient moe model with high capability.

These figures are estimates derived from hardware specifications and API benchmarks — DeepSeek has not published official energy data for DeepSeek-V3. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

DeepSeek-V3 in context

24 MWhestimated daily

At global scale

With an estimated 10M+ daily users averaging 10 queries each, DeepSeek-V3 consumes roughly 24 MWh of electricity per day — enough to power 800 homes.

2.2 kWhper year

Your yearly DeepSeek-V3 footprint

At 25 queries per day, your annual DeepSeek-V3 usage consumes 2.2 kWh — comparable to running a LED light bulb for a month. That produces 1.2 kg of CO₂.

Key insights

  • Open-source weights — can be self-hosted on infrastructure you control

The DeepSeek DeepSeek family

One chart per tier, on a shared time axis. Hover a dot for details; click to open that version.

Newer in this tier: DeepSeek-V3.2 uses 0.25 Wh per query, 4% more than DeepSeek-V3.

8 versions across 3 tiers. Lightest: DeepSeek-V4-Flash (0.10 Wh); heaviest: DeepSeek-R1 (1.2 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 DeepSeek-V3 usage cost the planet?

Use the calculator to estimate your personal footprint based on how often you use DeepSeek-V3.

Calculate my compute

Frequently asked questions

How much energy does DeepSeek-V3 use per query?

Each DeepSeek-V3 query consumes approximately 0.24 Wh of energy. This is about the same as a traditional Google search (~0.3 Wh).

What is DeepSeek-V3's carbon footprint?

Based on the carbon intensity of China (Hangzhou / Hainan), each query produces approximately 0.13 g of CO2. The grid in this region has a carbon intensity of 525 g CO2/kWh with 33% renewable energy.

How much water does DeepSeek-V3 use?

Each query consumes approximately 0.89 mL of water, primarily used for cooling the data centers that process the request.

How does DeepSeek-V3 compare to a Google search?

A DeepSeek-V3 query uses about the same as a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while DeepSeek-V3 uses 0.24 Wh.

Technical details

Architecture
Transformer Mixture-of-Experts (decoder-only)
Parameters
671B
Context window
128,000 tokens
Release date
2024-12-26
Open source
Yes

Sources