Berget AI releases open-source per-request carbon accounting method
Berget AI, Stockholm Environment Institute, WattTime and Klimatkollen released an MIT-licensed method for calculating the carbon emissions of individual AI requests. It follows the Green Software Foundation’s SCI for AI specification and uses average regional grid intensity plus hardware-manufacturing emissions. Berget AI says customers can track request-level emissions in its console. For one Kimi K3 request, the corrected estimate was 0.38 grams of CO₂e in Sweden and 3.2 grams in Texas, an 8.5-fold difference on identical hardware. Current estimates exclude training emissions and the water and energy footprint of chip manufacturing; marginal-emission estimates were planned for a later update.
The method is intended to let buyers compare AI providers using per-request emissions data rather than provider averages or marketing claims, and Berget AI says it hopes to encourage more providers to publish comparable figures.
Estimates based on the average emissions intensity of each regional electricity grid*
STOCKHOLM, 21 October 2026. Swedish AI provider Berget AI today releases an open-source method for calculating the carbon emissions of every individual AI request, developed with researchers from Stockholm Environment Institute (SEI) and the tech non-profits WattTime and Klimatkollen. Berget AI's customers can follow their own emissions in the company's console as they use the service. By making the method free for anyone to use, Berget AI wants more AI providers to report emissions per request, so that buyers can compare providers on real figures and choose lower-carbon options.
"Most companies today have no way of knowing what their use of AI emits. With this method our customers can follow their emissions request by request and compare providers on data instead of marketing. We know most European buyers would choose differently if they could see the numbers," says Andreas Lundmark, CEO of Berget AI.
A typical request to the open model Kimi K3 emits about 0.4 grams of CO₂ in Sweden, 1.6 grams in Ireland, 2.5 grams in Germany and 3.2 grams in Texas, on identical hardware — 8.5 times more in Texas than in Sweden. The result also depends on the model, the time of day and whether part of the prompt is cached, so the method calculates each request separately instead of applying an average. Berget AI reports location-based figures, using the average grid mix where the servers run, and includes the emissions from manufacturing the hardware.
#Berget AI#Stockholm Environment Institute#WattTime#Klimatkollen#@bergetai/co2-calculator 1.1.1#Kimi K3#Green Software Foundation