Microsoft ONNX Runtime Open-Source Inference Engine

Explore this developer service’s free allowance, critical restrictions and official documentation before deploying.

INCLUDED FREE ALLOWANCE

MIT-licensed cross-platform machine-learning inference runtime with CPU and supported hardware acceleration for ONNX models; no vendor software API quota or license seat fee.

Plan details

Plan: Ongoing free allowance
Deployment model: Local / embedded
Credit card: Not required
Commercial use: Allowed
Added to directory (UTC): 2026-10-29
Last checked: 2026-10-29

Important restrictions

Run inference on your own devices or infrastructure; model weights, GPU/accelerator hardware, cloud compute and third-party services may cost extra. Some distribution builds collect usage telemetry; model licenses are separate.

View official documentation

Independent community listing, not affiliated with the provider. Always check the latest billing policy and quotas before enabling paid usage.