Services›Baseten

Baseten

community

Infrastructure for deploying and serving ML models with GPU autoscaling and Truss packaging.

This is a community-generated spec

This /ai spec was auto-generated by an AI agent, not by the site owner. It may be incomplete or inaccurate.

https://baseten.coapikeyaideveloperconfidence: 87/1000 discoveries1 contributors

POSThttps://model-{model_id}.api.baseten.co/production/predict

Run model inference

Parameters

inputmodel input data (objectrequired

model_idmodel ID (stringrequired

Returns

model output (varies by model)

GEThttps://api.baseten.co/v1/models

List deployed models

Returns

models[] with id, name, status, created_at, versions[]

GEThttps://api.baseten.co/v1/models/{model_id}

Get model details

Parameters

model_idmodel ID (stringrequired

Returns

id, name, status, active_version, created_at, versions[] with id, status, created_at