ML Model Gateway

Models
3
Requests
3

Models

ID Name Framework Version Status Deployed Latency (ms)
m-001 text-classifier TensorFlow 1.0.0 serving 2026-07-01 45.0
m-002 image-detector PyTorch 2.1.0 serving 2026-07-06 120.0
m-003 recommender ONNX 1.2.0 stopped 2026-07-10 80.0

Inference Requests

Request ID Model ID Timestamp Input (KB) Output (KB) Status
req-001 m-001 2026-07-11 05:45 1.5 0.8 success
req-002 m-001 2026-07-11 05:50 2.0 1.2 success
req-003 m-002 2026-07-11 05:53 5.0 3.5 error

Endpoints

Model ID Endpoint Method Auth Type Rate Limit
m-001 /v1/predict POST api-key 1000