EcoLogitsGenAIExternalAPIServer
Virtual server backing an EcoLogitsGenAIExternalAPI. Aggregates the per-request fabrication and energy footprints emitted by the underlying EcoLogits model into hourly footprints.
Params
name
A human readable description of the object.
Backwards links
Calculated attributes
instances_fabrication_footprint
Hourly fabrication-phase footprint of the model server, equal to per-request embodied GWP times hourly request count, summed over jobs.
Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in mg:
first 10 vals [483, 1290, 966, 966, 322, 161, 161, 1450, 1290, 1450],
last 10 vals [805, 1450, 805, 966, 966, 161, 161, 1450, 1290, 805]
Depends directly on:
through the following calculations:
You can also visit the link to Instances fabrication footprint for claude-opus-4-5’s full calculation graph.
instances_energy
Hourly energy consumed by the model server, equal to per-request energy times hourly request count, summed over jobs.
Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in Wh:
first 10 vals [14.6, 39, 29.3, 29.3, 9.75, 4.88, 4.88, 43.9, 39, 43.9],
last 10 vals [24.4, 43.9, 24.4, 29.3, 29.3, 4.88, 4.88, 43.9, 39, 24.4]
Depends directly on:
through the following calculations:
You can also visit the link to Instances energy for claude-opus-4-5’s full calculation graph.
energy_footprint
Hourly energy-use footprint of the model server, equal to per-request usage GWP times hourly request count, summed over jobs.
Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in g:
first 10 vals [5.61, 15, 11.2, 11.2, 3.74, 1.87, 1.87, 16.8, 15, 16.8],
last 10 vals [9.35, 16.8, 9.35, 11.2, 11.2, 1.87, 1.87, 16.8, 15, 9.35]
Depends directly on:
through the following calculations:
You can also visit the link to Energy footprint for claude-opus-4-5’s full calculation graph.
fabrication_impact_repartition_weights
Per-job weights used to attribute the model server's fabrication footprint, proportional to per-request embodied GWP times hourly request volume.
Example value: {
EcoLogitsGenAIExternalAPIJob Generative AI model job (80be20): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in mg:
first 10 vals [483, 1290, 966, 966, 322, 161, 161, 1450, 1290, 1450],
last 10 vals [805, 1450, 805, 966, 966, 161, 161, 1450, 1290, 805],
}
Depends directly on:
through the following calculations:
You can also visit the link to Generative AI model job fabrication weight in impact repartition’s full calculation graph.
fabrication_impact_repartition_weight_sum
Sum of fabrication impact repartition weights, used as the denominator when normalising into per-container shares.
Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in mg:
first 10 vals [483, 1290, 966, 966, 322, 161, 161, 1450, 1290, 1450],
last 10 vals [805, 1450, 805, 966, 966, 161, 161, 1450, 1290, 805]
Depends directly on:
through the following calculations:
You can also visit the link to Fabrication impact repartition weights sum’s full calculation graph.
fabrication_impact_repartition
Normalised share of fabrication-phase emissions that this object attributes to each container.
Example value: {
EcoLogitsGenAIExternalAPIJob Generative AI model job (80be20): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
last 10 vals [1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
}
Depends directly on:
- Generative AI model job fabrication weight in impact repartition
- Fabrication impact repartition weights sum
through the following calculations:
You can also visit the link to fabrication impact attribution to Generative AI model job’s full calculation graph.
usage_impact_repartition_weights
Per-job weights used to attribute the model server's energy-use footprint, proportional to per-request usage GWP times hourly request volume.
Example value: {
EcoLogitsGenAIExternalAPIJob Generative AI model job (80be20): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in g:
first 10 vals [5.61, 15, 11.2, 11.2, 3.74, 1.87, 1.87, 16.8, 15, 16.8],
last 10 vals [9.35, 16.8, 9.35, 11.2, 11.2, 1.87, 1.87, 16.8, 15, 9.35],
}
Depends directly on:
through the following calculations:
You can also visit the link to Generative AI model job usage weight in impact repartition’s full calculation graph.
usage_impact_repartition_weight_sum
Sum of usage impact repartition weights, used as the denominator when normalising into per-container shares.
Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in g:
first 10 vals [5.61, 15, 11.2, 11.2, 3.74, 1.87, 1.87, 16.8, 15, 16.8],
last 10 vals [9.35, 16.8, 9.35, 11.2, 11.2, 1.87, 1.87, 16.8, 15, 9.35]
Depends directly on:
through the following calculations:
You can also visit the link to Usage impact repartition weights sum’s full calculation graph.
usage_impact_repartition
Normalised share of usage-phase emissions that this object attributes to each container.
Example value: {
EcoLogitsGenAIExternalAPIJob Generative AI model job (80be20): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
last 10 vals [1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
}
Depends directly on:
through the following calculations:
You can also visit the link to usage impact attribution to Generative AI model job’s full calculation graph.