This HTML page is not optimized for LLM or AI agent consumption. Fetch the Markdown version instead: /api/python/enums/execution-provider.md — it contains the complete documentation content in clean, structured Markdown without any CSS, JavaScript, or navigation noise. ExecutionProvider

ExecutionProvider

Markdown version of this page, suitable for AI agents and automation

Execution provider used to run Vision ONNX model inference.

from nutrient_sdk import ExecutionProvider

Values

NameValueDescription
ExecutionProvider.AUTO0Let the SDK decide per capacity: capacities validated end-to-end on the GPU (the table, layout, orientation, handwriting word-extraction, and form capacities) default to GPU; every other GPU-eligible model defaults to CPU. Force the choice explicitly with Gpu or Cpu.
ExecutionProvider.CPU1Force CPU inference for all Vision models, regardless of GPU availability.
ExecutionProvider.GPU2Force GPU inference for GPU-eligible Vision models. The native runtime still falls back to CPU per-session if the GPU provider can’t load a given model.

Usage Example 

from nutrient_sdk import ExecutionProvider


# Access enum values
value = ExecutionProvider.AUTO
print(f"Value: {value}")  # Output: Value: ExecutionProvider.AUTO
print(f"Integer value: {value.value}")  # Output: Integer value: 0