Skip to content

EcoLogitsVideoGenExternalAPI

An external generative-AI video API (Sora, Veo, Kling, Seedance, Runway, ...) modeled through the EcoLogits library. Picks a provider and model from the EcoLogits video catalog; datacenter location, PUE and WUE are looked up in the EcoLogits per-provider config.

Usage from Python

Pick EcoLogitsVideoGenExternalAPI.provider and EcoLogitsVideoGenExternalAPI.model_name from the EcoLogits video catalog, then attach EcoLogitsVideoGenExternalAPIJobs sized by resolution, duration and whether audio is generated.

Params

name

A human readable description of the object.

provider

Provider key parsed from the EcoLogits video catalog (e.g. openai, google, klingai).

For example, openai.

model_name

Specific video model name (after the provider/ prefix) from the chosen provider's EcoLogits video catalog. Drives the hardware configuration and the latency-regression coefficients.

For example, sora-2-pro.

Calculated attributes

datacenter_location

Geographic zone where the provider's datacenter runs, looked up in the EcoLogits video provider config. Drives which electricity mix is applied.

Example value: USA

Depends directly on:

through the following calculations:

You can also visit the link to Datacenter location for openai’s full calculation graph.

data_center_pue

Power Usage Effectiveness of the provider's datacenter, looked up in the EcoLogits video provider config.

Example value: 1.2

Depends directly on:

through the following calculations:

You can also visit the link to Datacenter PUE for openai’s full calculation graph.

average_carbon_intensity

Average grid carbon intensity at the datacenter location, looked up in the EcoLogits electricity mix repository.

Example value: 0.384 kg/kWh

Depends directly on:

through the following calculations:

You can also visit the link to Average carbon intensity of electricity mix for openai’s full calculation graph.