Bridge — Export & Deploy

Cross freely. Leave nothing behind.

Zero lock-in. Export your model in open formats and deploy it where it runs best for you. From local services to production APIs, BreezeML keeps it practical.

Export a model See a deployed API

An arched wooden bridge crossing a quiet stream in mist

Export model

Choose format

Python package

Native Python package for easy integration

ONNX

Open standard for cross-framework ML

PMML

For Java ecosystems and enterprise use

JSON

Lightweight format for portability

Docker

Containerized model for consistent runtime

Artifacts

Exported 3 minutes ago · Churn v1

churn_model_v1_python.zip1.2 MB

Includes model, metadata.json, schema.json, README.md

Load exported model

from breezeml import BreezeModel
model = BreezeModel.load("churn_model_v1")
preds = model.predict(df)
proba = model.predict_proba(df)

Deployment preview

Running

Served via a lightweight FastAPI app.

Base URL

https://churn-model-v1.breezeml.app

Endpoints

POST/predictMake predictions
GET/healthHealth check
GET/docsInteractive API docs

Deploy

Choose deployment target

BreezeML Managed ⌄

Deployed 2 minutes ago

RuntimePython 3.10

Frameworkscikit-learn 1.4.2

Instance1 vCPU, 2 GB

Regionus-east-1

Deployment status

Latency (P50)

42 ms

Requests (24h)

12,842

Error Rate

0.02%

Uptime

99.98%

Next: visit the Agent Shrine, where AI agents train and deploy with sound defaults.

Continue to the Shrine