3.4× less energy than DeepSeek-V3.
DeepSeek-V3 Environmental Impact
Efficient MoE model with high capability
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)
80% of a Google search.
About 1.1× a Google search and 6% of 10 m by car.
About 18× a drop of water and 18% of a teaspoon of water.
- 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.
Want something lighter?
1.6× less energy than DeepSeek-V3.
4.0× less energy than DeepSeek-V3.
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.
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
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.
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