Artificial Intelligence Bearer Token

AI APIs REST API

Universal interface for AI model inference and deployment

AI APIs provides a unified REST interface for deploying and interacting with machine learning models across multiple frameworks and providers. Developers use it to integrate natural language processing, computer vision, and generative AI capabilities into applications without managing infrastructure. The API abstracts complexity while offering granular control over model parameters, making it ideal for production AI workflows.

Base URL https://api.aiapi.rest/v1

API Endpoints

Method	Endpoint	Description
POST	`/models/inference`	Run inference on a deployed AI model with input data and parameters
GET	`/models`	List all available AI models with filtering and pagination
GET	`/models/{modelId}`	Retrieve detailed information about a specific AI model
POST	`/models/deploy`	Deploy a new AI model from supported frameworks or registries
DELETE	`/models/{modelId}`	Delete a deployed model and release its resources
POST	`/embeddings`	Generate vector embeddings from text or image inputs
POST	`/chat/completions`	Generate conversational responses using language models
POST	`/images/generate`	Create images from text prompts using generative models
POST	`/transcriptions`	Transcribe audio files to text using speech recognition models
POST	`/classifications`	Classify text or images into predefined categories
GET	`/jobs/{jobId}`	Check the status of an asynchronous inference job
POST	`/models/{modelId}/finetune`	Start a fine-tuning job for a base model with custom data
GET	`/usage`	Retrieve API usage statistics and token consumption metrics
POST	`/batch/inference`	Submit multiple inference requests for batch processing
GET	`/models/{modelId}/metrics`	Get performance metrics and latency statistics for a model

Code Examples

curl -X POST https://api.aiapi.rest/v1/models/inference \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
    "model_id": "gpt-4-turbo",
    "inputs": {
      "prompt": "Explain quantum computing in simple terms",
      "max_tokens": 150,
      "temperature": 0.7
    }
  }'

const response = await fetch('https://api.aiapi.rest/v1/models/inference', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_id: 'gpt-4-turbo',
    inputs: {
      prompt: 'Explain quantum computing in simple terms',
      max_tokens: 150,
      temperature: 0.7
    }
  })
});

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

import requests

url = 'https://api.aiapi.rest/v1/models/inference'
headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Content-Type': 'application/json'
}
payload = {
    'model_id': 'gpt-4-turbo',
    'inputs': {
        'prompt': 'Explain quantum computing in simple terms',
        'max_tokens': 150,
        'temperature': 0.7
    }
}

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

Connect AI APIs to AI

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

ai_model_inference Execute AI model inference with natural language prompts and return structured results for autonomous decision-making

ai_embedding_search Generate embeddings and perform semantic search across vector databases to find contextually relevant information

ai_batch_processor Process multiple AI tasks in parallel for efficient bulk operations like document analysis or image classification

ai_model_selector Intelligently select the optimal AI model based on task requirements, latency constraints, and cost considerations

ai_finetune_manager Manage model fine-tuning workflows including dataset preparation, training monitoring, and deployment automation

Deploy in 60 seconds

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

Deploy AI APIs MCP Server →

AI APIs REST API

API Endpoints

Code Examples

Connect AI APIs to AI

Deploy in 60 seconds

Related APIs