Skip to content

EcoLogitsGenAIExternalAPIJob

Params

name

A human readable description of the object.

external_api

An instance of EcoLogitsGenAIExternalAPI.

output_token_count

Output token count for claude-opus-4-5 in dimensionless.

Calculated attributes

data_transferred

ExplainableQuantity in kilobyte, representing the Data transferred for claude-opus-4-5.

Example value: 5 kB

Depends directly on:

through the following calculations:

You can also visit the link to Data transferred for claude-opus-4-5’s full calculation graph.

impacts

Example value: {'model_active_parameter_count': 133.5, 'model_total_paramet...

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits impacts for Generative AI model job from Ecologits compute_llm_impacts_dag function’s full calculation graph.

gpu_energy

ExplainableQuantity in watt_hour, representing the Ecologits gpu_energy for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 117 mWh

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits gpu_energy for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

generation_latency

ExplainableQuantity in second, representing the Ecologits generation_latency for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 30.9 s

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits generation_latency for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

model_required_memory

ExplainableQuantity in gigabyte, representing the Ecologits model_required_memory for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 1.61 TB

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits model_required_memory for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

gpu_required_count

ExplainableQuantity in dimensionless, representing the Ecologits gpu_required_count for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 32

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits gpu_required_count for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

server_energy

ExplainableQuantity in watt_hour, representing the Ecologits server_energy for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 644 mWh

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits server_energy for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

request_energy

ExplainableQuantity in watt_hour, representing the Ecologits request_energy for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 4.88 Wh

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits request_energy for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

request_usage_gwp

ExplainableQuantity in gram, representing the Ecologits request_usage_gwp for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 1.87 g

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits request_usage_gwp for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

server_gpu_embodied_gwp

ExplainableQuantity in kilogram, representing the Ecologits server_gpu_embodied_gwp for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 31.5 t

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits server_gpu_embodied_gwp for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

request_embodied_gwp

ExplainableQuantity in gram, representing the Ecologits request_embodied_gwp for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 161 mg

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits request_embodied_gwp for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

request_duration

ExplainableQuantity in second, representing the Ecologits generation_latency for claude-opus-4-5 from ecologits compute_llm_impacts_dag function.

Example value: 30.9 s

Depends directly on:

through the following calculations:

You can also visit the link to Ecologits generation_latency for claude-opus-4-5 from Ecologits compute_llm_impacts_dag function’s full calculation graph.

hourly_occurrences_per_usage_pattern

Dictionary with UsagePattern as keys and Hourly generative ai model job occurrences in usagepattern usage pattern as values, in occurrence.

Example value: {
UsagePattern usage pattern (7703de): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [6, 6, 1, 1, 7, 7, 1, 7, 9, 1],
last 10 vals [7, 1, 3, 1, 7, 5, 6, 3, 3, 4],
}

Depends directly on:

through the following calculations:

You can also visit the link to Hourly Generative AI model job occurrences in UsagePattern usage pattern’s full calculation graph.

hourly_avg_occurrences_per_usage_pattern

Dictionary with UsagePattern as keys and Average hourly generative ai model job occurrences in usage pattern as values, in concurrent.

Example value: {
UsagePattern usage pattern (7703de): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [0.0515, 0.0515, 0.00859, 0.00859, 0.0601, 0.0601, 0.00859, 0.0601, 0.0773, 0.00859],
last 10 vals [0.0601, 0.00859, 0.0258, 0.00859, 0.0601, 0.0429, 0.0515, 0.0258, 0.0258, 0.0344],
}

Depends directly on:

through the following calculations:

You can also visit the link to Average hourly Generative AI model job occurrences in usage pattern’s full calculation graph.

hourly_data_transferred_per_usage_pattern

Dictionary with UsagePattern as keys and Hourly data transferred for generative ai model job in usage pattern as values, in megabyte.

Example value: {
UsagePattern usage pattern (7703de): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in kB:
first 10 vals [30, 30, 5, 5, 35, 35, 5, 35, 45, 5],
last 10 vals [35, 5, 15, 5, 35, 25, 30, 15, 15, 20],
}

Depends directly on:

through the following calculations:

You can also visit the link to Hourly data transferred for Generative AI model job in usage pattern’s full calculation graph.

hourly_data_stored_per_usage_pattern

Dictionary with UsagePattern as keys and Hourly data stored for generative ai model job in usage pattern as values, in megabyte.

Example value: {
UsagePattern usage pattern (7703de): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in B:
first 10 vals [0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
last 10 vals [0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
}

Depends directly on:

through the following calculations:

You can also visit the link to Hourly data stored for Generative AI model job in usage pattern’s full calculation graph.

hourly_avg_occurrences_across_usage_patterns

Hourly generative ai model job average occurrences across usage patterns in concurrent.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [0.0515, 0.0515, 0.00859, 0.00859, 0.0601, 0.0601, 0.00859, 0.0601, 0.0773, 0.00859],
last 10 vals [0.0601, 0.00859, 0.0258, 0.00859, 0.0601, 0.0429, 0.0515, 0.0258, 0.0258, 0.0344]

Depends directly on:

through the following calculations:

You can also visit the link to Hourly Generative AI model job average occurrences across usage patterns’s full calculation graph.

hourly_data_transferred_across_usage_patterns

Hourly generative ai model job data transferred across usage patterns in megabyte.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in kB:
first 10 vals [30, 30, 5, 5, 35, 35, 5, 35, 45, 5],
last 10 vals [35, 5, 15, 5, 35, 25, 30, 15, 15, 20]

Depends directly on:

through the following calculations:

You can also visit the link to Hourly Generative AI model job data transferred across usage patterns’s full calculation graph.

hourly_data_stored_across_usage_patterns

Hourly generative ai model job data stored across usage patterns in megabyte.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in B:
first 10 vals [0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
last 10 vals [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]

Depends directly on:

through the following calculations:

You can also visit the link to Hourly Generative AI model job data stored across usage patterns’s full calculation graph.

fabrication_impact_repartition_weights

Dictionary with UsageJourneyStep as keys and 20 min streaming weight in generative ai model job impact repartition as values, in concurrent.

Example value: {
UsageJourneyStep 20 min streaming (624221): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [2, 2, 0.333, 0.333, 2.33, 2.33, 0.333, 2.33, 3, 0.333],
last 10 vals [2.33, 0.333, 1, 0.333, 2.33, 1.67, 2, 1, 1, 1.33],
}

Depends directly on:

through the following calculations:

You can also visit the link to 20 min streaming weight in Generative AI model job impact repartition’s full calculation graph.

fabrication_impact_repartition_weight_sum

Sum of generative ai model job fabrication impact repartition weights in concurrent.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [2, 2, 0.333, 0.333, 2.33, 2.33, 0.333, 2.33, 3, 0.333],
last 10 vals [2.33, 0.333, 1, 0.333, 2.33, 1.67, 2, 1, 1, 1.33]

Depends directly on:

through the following calculations:

You can also visit the link to Sum of Generative AI model job fabrication impact repartition weights’s full calculation graph.

fabrication_impact_repartition

Dictionary with UsageJourneyStep as keys and Generative ai model job fabrication impact attribution to 20 min streaming as values, in concurrent.

Example value: {
UsageJourneyStep 20 min streaming (624221): 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 Generative AI model job fabrication impact attribution to 20 min streaming’s full calculation graph.

usage_impact_repartition_weights

Dictionary with UsageJourneyStep as keys and 20 min streaming weight in generative ai model job impact repartition as values, in concurrent * gram / kilowatt_hour.

Example value: {
UsageJourneyStep 20 min streaming (624221): 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in ·g/kWh:
first 10 vals [170, 170, 28.3, 28.3, 198, 198, 28.3, 198, 255, 28.3],
last 10 vals [198, 28.3, 85, 28.3, 198, 142, 170, 85, 85, 113],
}

Depends directly on:

through the following calculations:

You can also visit the link to 20 min streaming weight in Generative AI model job impact repartition’s full calculation graph.

usage_impact_repartition_weight_sum

Sum of generative ai model job usage impact repartition weights in concurrent * gram / kilowatt_hour.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in ·g/kWh:
first 10 vals [170, 170, 28.3, 28.3, 198, 198, 28.3, 198, 255, 28.3],
last 10 vals [198, 28.3, 85, 28.3, 198, 142, 170, 85, 85, 113]

Depends directly on:

through the following calculations:

You can also visit the link to Sum of Generative AI model job usage impact repartition weights’s full calculation graph.

usage_impact_repartition

Dictionary with UsageJourneyStep as keys and Generative ai model job usage impact attribution to 20 min streaming as values, in concurrent.

Example value: {
UsageJourneyStep 20 min streaming (624221): 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 Generative AI model job usage impact attribution to 20 min streaming’s full calculation graph.

hourly_occurrences_across_usage_patterns

Hourly generative ai model job occurrences across usage patterns in occurrence.

Example value: 26298 values from 2025-01-01 00:00:00+00:00 to 2028-01-01 18:00:00+00:00 in :
first 10 vals [6, 6, 1, 1, 7, 7, 1, 7, 9, 1],
last 10 vals [7, 1, 3, 1, 7, 5, 6, 3, 3, 4]

Depends directly on:

through the following calculations:

You can also visit the link to Hourly Generative AI model job occurrences across usage patterns’s full calculation graph.