Text / ChatLowEstimatedReleased 2026-07-16

Kimi K3 Environmental Impact

Largest open-weight model to date — 2.8T-parameter MoE with native vision

ArchitectureMixture-of-Experts (2.8T total) with native visionParameters2800BContext1,000,000 tokensProviderMoonshot AI

The figures below are for one quick question. A longer chat with follow-ups uses about 2.3 Wh, and an hour or two of agent work about 65.0 Wh.

One query, in context

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

Energy0.65Wh per query

About 2.2× a Google search and 78% of a minute of laptop use.

likely 0.33 Wh – 1.3 Wh
Carbon0.34g per query

About 2.8× a Google search and 16% of 10 m by car.

likely 0.17 g – 0.68 g
Water2mL per query

About 48× a drop of water and 48% of a teaspoon of water.

likely 1 mL – 5 mL
  • Where it runsMoonshot AI Cloud (China) / self-hosted
  • Grid carbon intensity525 g CO₂/kWh · 33% renewable
  • Compared with a Google search2x more than a search (0.3 Wh)
  • Water~417 queries to fill 1 litre

Where Kimi K3 sits

#133 of 199 by energy per query. Heavier than 66% 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 WhDeepSeek-V3 — 0.24 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 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 kWhKimi K3

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
70.4 Wh
Carbon
36.8 g
Water
260 mL

A month of 5 chats a day, 5 days a week. The energy is about 5.9× a phone charge and 64% of a kettle boil.

Work out your own →
Energy
281.4 Wh
Carbon
147.2 g
Water
1.04 L

A month of 20 chats a day, 5 days a week. The energy is about 2.6× a kettle boil and 4% of a UK home's day.

Work out your own →
Energy
1.41 kWh
Carbon
736.1 g
Water
5.20 L

A month of 100 chats a day, 5 days a week. The energy is about 13× a kettle boil and 19% of a UK home's day.

Work out your own →

How does Kimi K3 compare?

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

Kimi K2.50.30 Wh
GPT-5.20.61 Wh
Kimi K30.65 Wh

Detailed breakdown

Energy

Kimi K3 is one of the few frontier-scale models whose energy has actually been benchmarked rather than inferred: because the weights are open, CLEER (Sustainable AI Group, Sept 2026) ran it directly on eight B300 accelerators and measured ~0.65 Wh for a quick single question, ~2.3 Wh for a typical multi-turn chat and ~88 Wh for a typical agentic session — full-facility figures including host servers, idle capacity and cooling. That makes it the heaviest open model in the dataset, and it is the main proxy CLEER uses to estimate Claude Fable 5. Weights followed the 16 July launch on 27 July under a custom licence.

Power source & carbon

Hosted inference runs on the Chinese grid at ~525 gCO2/kWh (Ember 2026). Open weights mean it is also widely self-hosted, where the footprint depends entirely on the local grid.

Water use

At ~2.4 mL per quick question on Chinese infrastructure (3.7 L/kWh combined water factor).

About Kimi K3

Kimi K3 is a 2800B-parameter text and chat model from Moonshot AI, released July 16, 2026. Largest open-weight model to date — 2.8T-parameter MoE with native vision. At 0.65 Wh per query, it uses 2x the energy of a Google search. It runs on a Mixture-of-Experts (2.8T total) with native vision architecture.

These figures are estimates derived from hardware specifications and API benchmarks — Moonshot AI has not published official energy data for Kimi K3. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Kimi K3 in context

98%potential savings

The efficiency alternative

Gemini Nano performs the same type of task using just 0.01 Wh per query — 98% less energy than Kimi K3. For a user sending 25 queries per day, switching would save 5.8 kWh per year.

5.9 kWhper year

Your yearly Kimi K3 footprint

At 25 queries per day, your annual Kimi K3 usage consumes 5.9 kWh — comparable to running a LED light bulb for a month. That produces 3.1 kg of CO₂.

Key insights

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

The Moonshot AI Kimi family

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

Kimi: 0.25 Wh · Mar 2024Kimi0.25 WhKimi K2.5: 0.30 Wh · Jan 2026Kimi K2.50.30 WhKimi K3: 0.65 Wh · Jul 2026Kimi K30.65 WhMar 2024Jul 2026
Kimi to Kimi K3: 160% higher energy per query across 3 versions.

What does your Kimi K3 usage cost the planet?

Use the calculator to estimate your personal footprint based on how often you use Kimi K3.

Calculate my compute

Frequently asked questions

How much energy does Kimi K3 use per query?

Each Kimi K3 query consumes approximately 0.65 Wh of energy. This is 2x more than a traditional Google search (~0.3 Wh).

What is Kimi K3's carbon footprint?

Based on the carbon intensity of Moonshot AI Cloud (China) / self-hosted, each query produces approximately 0.34 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 Kimi K3 use?

Each query consumes approximately 2 mL of water, primarily used for cooling the data centers that process the request.

How does Kimi K3 compare to a Google search?

A Kimi K3 query uses 2x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Kimi K3 uses 0.65 Wh.

Technical details

Architecture
Mixture-of-Experts (2.8T total) with native vision
Parameters
2800B
Context window
1,000,000 tokens
Release date
2026-07-16
Open source
Yes

Sources