📚 API Documentation

OpenAI-compatible API with automatic load balancing and health monitoring

🔐 Authentication

All API requests (except /health) require authentication using an API key. Include your API key in the Authorization header:

Authorization: Bearer your-api-key-here

🌐 Base URL

https://vibeapi.vip

📡 API Endpoints

Health Check

GET

Check the health status of all backend servers

Endpoint: /health

Request Example

curl https://vibeapi.vip/health

Response Example

{
  "servers": [
    {
      "url": "https://backend1.example.com",
      "healthy": true,
      "lastCheck": 1777874496223,
      "responseTime": 1833,
      "consecutiveFailures": 0
    },
    {
      "url": "https://backend2.example.com",
      "healthy": true,
      "lastCheck": 1777874496222,
      "responseTime": 1831,
      "consecutiveFailures": 0
    }
  ],
  "totalServers": 2,
  "healthyServers": 2,
  "lastUpdate": 1777874496223
}

List Models

GET🔒 Auth Required

Get a list of available AI models

Endpoint: /v1/models

Request Example

curl https://vibeapi.vip/v1/models \
  -H "Authorization: Bearer your-api-key-here" \
  -H "Content-Type: application/json"

Response Example

{
  "object": "list",
  "data": [
    {
      "id": "claude-sonnet-4.5",
      "object": "model",
      "created": 1777874512,
      "owned_by": "anthropic",
      "description": "Claude model via Kiro API"
    },
    {
      "id": "claude-haiku-4.5",
      "object": "model",
      "created": 1777874512,
      "owned_by": "anthropic",
      "description": "Claude model via Kiro API"
    }
  ]
}

Chat Completions

POST🔒 Auth Required

Create a chat completion with AI models

Endpoint: /v1/chat/completions

Request Example

curl -X POST https://vibeapi.vip/v1/chat/completions \
  -H "Authorization: Bearer your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 100
  }'

Response Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1777874512,
  "model": "claude-sonnet-4.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Streaming Chat Completions

POST🔒 Auth Required

⚠️ Currently not supported through load balancer. Use backend URLs directly for streaming.

Endpoint: /v1/chat/completions

Request Example

# Streaming through load balancer is not currently supported
# Use backend URL directly for streaming:
curl -N -X POST https://kiro-gateway-production-07e4.up.railway.app/v1/chat/completions \
  -H "Authorization: Bearer your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [
      {"role": "user", "content": "Tell me a story"}
    ],
    "stream": true,
    "max_tokens": 200
  }'

Response Example

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1777874512,"model":"claude-sonnet-4.5","choices":[{"index":0,"delta":{"role":"assistant","content":"Once"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1777874512,"model":"claude-sonnet-4.5","choices":[{"index":0,"delta":{"content":" upon"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1777874512,"model":"claude-sonnet-4.5","choices":[{"index":0,"delta":{"content":" a"},"finish_reason":null}]}

data: [DONE]

✨ Features

🔄 Load Balancing: Automatic round-robin distribution across healthy backends
🏥 Health Monitoring: Continuous health checks every 30 seconds
🚀 Auto Failover: Unhealthy servers automatically excluded from rotation
📊 Performance Tracking: Real-time response time monitoring
🔒 Secure: API key authentication and HTTPS encryption
🌐 OpenAI Compatible: Drop-in replacement for OpenAI API

⚠️ Current Limitations

Streaming Not Supported Through Load Balancer

Due to Vercel Serverless Functions limitations, streaming responses (stream: true) are not currently supported through the load balancer.

Workaround: For streaming responses, use the backend URLs directly:

Backend 1: https://kiro-gateway-production-07e4.up.railway.app/v1
Backend 2: https://kiro-gateway-kiroaccount-pool-a.up.railway.app/v1

Note: Using backend URLs directly bypasses load balancing and automatic failover features.

💻 SDK Examples

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key-here",
    base_url="https://vibeapi.vip/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4.5",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

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

Node.js (OpenAI SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-api-key-here',
  baseURL: 'https://vibeapi.vip/v1',
});

const response = await client.chat.completions.create({
  model: 'claude-sonnet-4.5',
  messages: [
    { role: 'user', content: 'Hello!' }
  ],
});

console.log(response.choices[0].message.content);

⚠️ Error Codes

Status Code	Error	Description
401	Unauthorized	Invalid or missing API key
503	Service Unavailable	No healthy backend servers available
500	Internal Server Error	Failed to forward request to backend