⌘K

Quickstart

Get started with Vtrix API in 5 minutes. This guide shows how to use LLM models and multi-modal models.

Authentication

Create Your API Key

Before you begin, you need an API key. Go to Settings to create one.

Step 1: Click the “Create API Key” button

Step 2: Give your API Key a descriptive name

Step 3: Save and copy the generated API Key (shown only once)

Using Your API Key

Include your API key in the Authorization header of every API request:

Authorization: Bearer YOUR_API_KEY

API Key Security Best Practices

Use Environment Variables: Store your API Key in environment variables, never hardcode it in source code

Server-Side Only: Always make API calls from your backend, never directly from browsers or mobile apps

Regular Rotation: Regularly rotate your API Keys, especially if you suspect they may have been compromised

Least Privilege: Create separate API Keys for different applications for easier management and revocation

If you believe your API Key has been compromised, immediately revoke it in your Settings and create a new one.

Use LLM Models (Text Chat)

Chat with any LLM model. Here are complete code examples:

curl 'https://cloud.vtrix.ai/llm/chat/completions' \
 -H "Authorization: Bearer YOUR_API_KEY" \
 -H 'Content-Type: application/json' \
 -d '{ 
 	"model": "vtrix-gpt-5", 
 	"messages": [{"role":"user","content":"hello"}] 
 }'

Use AI Agents (Specialized Capabilities)

AI Agents are specialized AI assistants with tool-calling and multi-modal capabilities:

curl https://cloud.vtrix.ai/agent/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $YOUR_API_KEY" \
-H "X-Project: Vtrix" \
-d '{
  "agent_id": "seagen_agent",
  "model":"vtrix-gpt-4.1",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Hello, please introduce yourself."
        }
      ]
    }
  ]
}'

Visit Agent Studio to browse available Agents, or see Agent API docs for detailed usage.

Use Multi-Modal Models (Image Generation)

Generate images using Google Gemini 3 Pro Image. This example shows how to call multi-modal models:

curl --location 'https://cloud.vtrix.ai/model/v1/generation' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--data '{
  "model": "google_gemini3_pro_image",
  "input": [
    {
      "params": {
        "prompt": "example_prompt",
        "image_urls": [
          "https://example.com/image.jpg"
        ],
        "aspect_ratio": "1:1",
        "resolution": "1K"
      }
    }
  ]
}'