API Reference

Comprehensive API documentation for integrating Transium's AI infrastructure into your applications. RESTful APIs, SDKs, and code examples to get you started quickly.

RESTful APIs

Simple, intuitive REST APIs for model deployment, training, and infrastructure management.

Authentication

Secure API key authentication with role-based access control and rate limiting.

SDKs & Libraries

Official SDKs for Python, JavaScript, Go, and more with comprehensive documentation.

Real-time APIs

WebSocket and streaming APIs for real-time model inference and monitoring.

Enterprise Security

Enterprise-grade security with OAuth 2.0, SAML, and custom authentication options.

Global Endpoints

Regional API endpoints for low-latency access and data residency compliance.

Core API Endpoints

Model Management

GET

Create, deploy, and manage AI models across your infrastructure.

GET /api/v1/models
POST /api/v1/models
PUT /api/v1/models/id

Training Jobs

POST

Submit and monitor distributed training jobs with automatic scaling.

POST /api/v1/training
GET /api/v1/training/job_id
DELETE /api/v1/training/job_id

Inference

POST

Run inference on deployed models with batch and real-time options.

POST /api/v1/inference
POST /api/v1/inference/batch
GET /api/v1/inference/status

Quick Start Example

Python SDK

# Install the SDK

pip install transium-sdk

# Initialize client

import

transium

client = transium.Client(

api_key="your-api-key"

)

# Deploy a model

model = client.models.deploy(

name="my-model",

framework="pytorch"

)

JavaScript SDK

// Install the SDK

npm install @transium/sdk

// Initialize client

import

TransiumClient

from

'@transium/sdk'

const

client = new TransiumClient({

apiKey: 'your-api-key'

});

// Deploy a model

const

model = await client.models.deploy({

name: 'my-model',

framework: 'tensorflow'

});