Axione AI Documentation

Welcome to the Axione AI API documentation. Our service provides a unified interface to access multiple AI models through a single, OpenAI-compatible API.

Base URL: https://axione.vercel.app/api/v1

Quick Start

Sign up for an account
Generate an API key from your dashboard
Start making requests to our API endpoints

Authentication

The Axione AI uses API keys for authentication. Include your API key in the Authorization header of all requests.

Authorization Header

Authorization: Bearer sk-your-api-key-here

Chat Completions

Create chat completions using various AI models. This endpoint is compatible with OpenAI's chat completions API.

POST /v1/chat/completions

Request Body:

{
  "model": "openai/gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "max_tokens": 150,
  "temperature": 0.7,
  "stream": false
}

Response:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm doing well, thank you for asking. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Available Models

Get a list of available AI models and their capabilities. All models follow the format provider/model-name.

GET /v1/models

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-4o",
      "object": "model",
      "created": 1677610602,
      "owned_by": "openai"
    },
    {
      "id": "anthropic/claude-3.5-sonnet",
      "object": "model",
      "created": 1687882411,
      "owned_by": "anthropic"
    },
    {
      "id": "google/gemini-2.5-flash-lite",
      "object": "model",
      "created": 1687882411,
      "owned_by": "google"
    }
  ]
}

Popular Models

OpenAI Models

openai/gpt-4o - Most advanced GPT-4 model
openai/gpt-4o-mini - Faster, cost-effective GPT-4
openai/gpt-3.5-turbo - Fast and efficient

Other Providers

anthropic/claude-3.5-sonnet - Advanced reasoning
google/gemini-2.5-flash-lite - Multimodal AI
mistral/mistral-large - Capable open model

Daily Limits

The API implements daily usage limits that are updated automatically every day. No subscriptions needed - your tier is updated based on usage patterns.

Tier	Requests/Day	Tokens/Day	Status
Tier 1	1,000	250,000	Free
Tier 2	4,000	1,000,000	Auto-upgrade
Tier 3	40,000	10,000,000	Auto-upgrade
Tier 4	80,000	20,000,000	Auto-upgrade
Tier 5	120,000	30,000,000	Premium

Daily Reset: All limits reset automatically at midnight UTC each day.

Error Handling

The API uses conventional HTTP response codes to indicate success or failure.

Error Response Format

{
  "error": {
    "type": "invalid_request_error",
    "message": "Model 'invalid/model' not found",
    "code": "model_not_found"
  }
}

Common Error Codes:

400 - Bad Request (invalid model format, missing parameters)
401 - Unauthorized (invalid API key)
404 - Not Found (model not found)
429 - Daily Limit Exceeded
500 - Internal Server Error

Code Examples

curl -X POST https://axione.vercel.app/api/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {
        "role": "user", 
        "content": "Hello!"
      }
    ]
  }'

const response = await fetch('https://axione.vercel.app/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-your-api-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'anthropic/claude-3.5-sonnet',
    messages: [
      { role: 'user', content: 'Hello!' }
    ]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

import openai

# Set up the client with your API key and base URL
client = openai.OpenAI(
    api_key="sk-your-api-key",
    base_url="https://axione.vercel.app/api/v1"
)

# Create a chat completion
response = client.chat.completions.create(
    model="google/gemini-2.5-flash-lite",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Documentation