Pipeline.ai
ML infrastructurePipeline.ai offered serverless GPU hosting for machine-learning models: a developer uploaded an ONNX model and called it through an API, paying only for the milliseconds the model actually ran.
- Category
- ML infrastructure
- Pricing model
- Pay per millisecond of inference
Listing compiled from public sources, not the vendor's original submission on this site. Check the tool's own website for current pricing and features.
Looking for something else? Browse all 63 tools across 44 categories.