AI/ML Platform Bearer Token

IOX Cloud REST API

Enterprise AI infrastructure and model orchestration API

IOX Cloud provides a unified REST API for deploying, managing, and orchestrating AI models across multi-cloud infrastructure. Developers use it to abstract away infrastructure complexity, scale ML workloads dynamically, and integrate multiple model providers through a single interface. The platform handles model versioning, A/B testing, traffic routing, and observability for production AI applications.

Base URL https://api.iox.cloud/v1

API Endpoints

Method	Endpoint	Description
GET	`/models`	List all deployed models with metadata, status, and performance metrics
POST	`/models`	Deploy a new model to the IOX Cloud infrastructure
GET	`/models/{modelId}`	Retrieve detailed information about a specific model deployment
PATCH	`/models/{modelId}`	Update model configuration, scaling rules, or deployment settings
DELETE	`/models/{modelId}`	Undeploy and remove a model from the infrastructure
POST	`/models/{modelId}/inference`	Execute inference requests against a deployed model
POST	`/models/{modelId}/batch`	Submit batch inference jobs for asynchronous processing
GET	`/models/{modelId}/metrics`	Retrieve real-time and historical performance metrics for a model
POST	`/experiments`	Create A/B testing experiments to compare model versions
GET	`/experiments/{experimentId}`	Get experiment details, traffic distribution, and performance results
GET	`/deployments`	List all active deployments across regions and environments
POST	`/deployments/{deploymentId}/scale`	Manually scale deployment resources or update autoscaling policies
GET	`/infrastructure/health`	Check infrastructure health status and resource availability
GET	`/logs`	Query model inference logs and system events with filtering
POST	`/webhooks`	Configure webhooks for deployment events, alerts, and metric thresholds

Code Examples

curl -X POST https://api.iox.cloud/v1/models/gpt-4-turbo/inference \
  -H 'Authorization: Bearer iox_sk_abc123xyz' \
  -H 'Content-Type: application/json' \
  -d '{
    "input": "Explain quantum computing",
    "max_tokens": 500,
    "temperature": 0.7
  }'

const response = await fetch('https://api.iox.cloud/v1/models/gpt-4-turbo/inference', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer iox_sk_abc123xyz',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    input: 'Explain quantum computing',
    max_tokens: 500,
    temperature: 0.7
  })
});

const data = await response.json();
console.log(data.output);

import requests

url = 'https://api.iox.cloud/v1/models/gpt-4-turbo/inference'
headers = {
    'Authorization': 'Bearer iox_sk_abc123xyz',
    'Content-Type': 'application/json'
}
payload = {
    'input': 'Explain quantum computing',
    'max_tokens': 500,
    'temperature': 0.7
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result['output'])

Connect IOX Cloud to AI

Deploy a IOX Cloud MCP server on IOX Cloud and connect it to Claude, ChatGPT, Cursor, or any AI client. Your AI assistant gets direct access to IOX Cloud through these tools:

deploy_model Deploy a new AI model to IOX Cloud infrastructure with specified configuration and scaling parameters

run_inference Execute inference requests against deployed models and return predictions or generated content

create_experiment Set up A/B testing experiments to compare different model versions or configurations

monitor_metrics Retrieve and analyze model performance metrics including latency, throughput, and accuracy

manage_scaling Adjust model deployment scaling policies and resource allocation based on traffic patterns

Deploy in 60 seconds

Describe what you need, AI generates the code, and IOX deploys it globally.

Deploy IOX Cloud MCP Server →

IOX Cloud REST API

API Endpoints

Code Examples

Connect IOX Cloud to AI

Deploy in 60 seconds

Related APIs