Vantico API Documentation

Build powerful AI applications with Vantico's OpenAI-compatible API. Access our Tico Free model with simple HTTP requests.

Quick Reference

Base URL	`https://vantico.xyz/api/v1`
Endpoint	`POST /chat/completions`
Authentication	`Authorization: Bearer VANTICO-...`
Model	Tico Free (model parameter optional)
SDK Compatibility	OpenAI Python & JavaScript SDKs
Streaming	Supported (set `stream: true`)

Authentication

All API requests require authentication using an API key. Include your API key in the Authorization header:

Authorization: Bearer VANTICO-XXXXXXXX-XXXXXXXX-XXXXXXXX-XXXXXXXX

Getting Your API Key

Sign in to your Vantico account
Click on your profile in the sidebar
Select "API Keys"
Click "Create New API Key"
Copy and save your key immediately

Important: Keep your API keys secure. Do not share them or commit them to version control.

Getting Started

Vantico's API is compatible with the OpenAI SDK, making it easy to integrate into your existing applications.

Quick Start

curl https://vantico.xyz/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Endpoints

Chat Completions

POST /chat/completions

Create a chat completion with the Tico Free model.

Request Body

Parameter	Type	Required	Description
`messages`	array	Yes	Array of message objects with role and content
`model`	string	No	Model identifier. Use "tico-free" or any value (ignored, defaults to Tico Free)
`temperature`	number	No	Sampling temperature (0-2). Default: 0.7
`max_tokens`	integer	No	Maximum tokens to generate. Default: 8000
`stream`	boolean	No	Enable streaming responses. Default: false

📝 Note on Model Parameter

The model parameter is optional and currently not used. All requests use the Tico Free model by default. You can omit this field or set it to any value (e.g., "tico-free", "gpt-3.5-turbo") for OpenAI SDK compatibility.

Message Roles

Each message object must include:

role: One of "system", "user", or "assistant"
content: The message text

Example message structure:

{
  "role": "user",
  "content": "What is the capital of France?"
}

Example Request

{
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is the capital of France?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1000
}

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "tico-free",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Streaming Responses

Enable streaming by setting "stream": true in your request. The response will be sent as Server-Sent Events (SSE).

Example Streaming Request

{
  "messages": [
    {"role": "user", "content": "Tell me a story"}
  ],
  "stream": true
}

Stream Response Format

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":"Once"}}]}

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":" upon"}}]}

data: {"id":"chatcmpl-123","choices":[{"delta":{"content":" a"}}]}

data: [DONE]

Code Examples

Python

Using the official OpenAI Python library:

from openai import OpenAI

client = OpenAI(
    api_key="VANTICO-XXXXXXXX-XXXXXXXX-XXXXXXXX-XXXXXXXX",
    base_url="https://vantico.xyz/api/v1"
)

response = client.chat.completions.create(
    model="tico-free",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing"}
    ],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)

Streaming Example

stream = client.chat.completions.create(
    model="tico-free",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

JavaScript / Node.js

Using the OpenAI JavaScript/TypeScript library:

import OpenAI from 'openai';

const client = new OpenAI({
    apiKey: 'VANTICO-XXXXXXXX-XXXXXXXX-XXXXXXXX-XXXXXXXX',
    baseURL: 'https://vantico.xyz/api/v1'
});

async function chat() {
    const response = await client.chat.completions.create({
        model: 'tico-free',
        messages: [
            { role: 'system', content: 'You are a helpful assistant.' },
            { role: 'user', content: 'What is JavaScript?' }
        ],
        temperature: 0.7,
        max_tokens: 500
    });
    
    console.log(response.choices[0].message.content);
}

chat();

Streaming Example

const stream = await client.chat.completions.create({
    model: 'tico-free',
    messages: [{ role: 'user', content: 'Tell me a joke' }],
    stream: true
});

for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

cURL

Direct HTTP requests using cURL:

curl https://vantico.xyz/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer VANTICO-XXXXXXXX-XXXXXXXX-XXXXXXXX-XXXXXXXX" \
  -d '{
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Error Handling

The API uses standard HTTP status codes to indicate success or failure.

Status Code	Meaning
`200`	Success
`400`	Bad Request - Invalid parameters
`401`	Unauthorized - Invalid or missing API key
`429`	Too Many Requests - Rate limit exceeded
`500`	Internal Server Error

Error Response Format

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Rate Limits

API requests share the same rate limits as the main Vantico platform. Rate limits are applied per underlying Groq API key, not per Vantico API key.

Best Practices

Implement exponential backoff for rate limit errors
Cache responses when possible
Use streaming for long responses
Monitor your usage patterns

Need Help?

If you have questions or need support, please:

Check our main platform for updates
Review the examples above
Ensure your API key is valid and active