SkyAIAppSkyAIApp
Get started

API Reference

SkyAIApp REST API v1.0

Complete API documentation covering authentication, model routing, agent runtime, and enterprise features.

Base URL

Production
https://api.skyaiapp.com/v1
Authentication
Model Routing
Agent Runtime
Analytics & Monitoring

Authentication

All API requests require authentication via API Key in the request header.

Request Header

Authorization: Bearer sk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Security Note

Never expose your API key in client-side code. Use a backend proxy for requests.

Example Request

curl -X POST https://api.skyaiapp.com/v1/route \
  -H "Authorization: Bearer sk_live_xxxx" \
  -H "Content-Type: application/json" \
  -d '{"goal": "cost", "messages": [{"role": "user", "content": "Hello"}]}'

Model Routing

POST/v1/route

Intelligently route requests to the optimal model based on goal and strategy.

Request Parameters

ParameterTypeRequiredDescription
messagesarrayArray of messages (OpenAI format)
goalstringOptimization goal: cost | quality | stability
strategystring-Strategy: balanced | cost-optimized | quality-first
streamboolean-Enable streaming response
max_tokensinteger-Maximum tokens to generate
temperaturenumber-Sampling temperature (0-2)
cacheboolean-Enable semantic caching

Request Example

{
  "goal": "cost",
  "strategy": "balanced",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain quantum computing in simple terms."}
  ],
  "max_tokens": 500,
  "temperature": 0.7,
  "cache": true
}

Response Example

{
  "id": "route_abc123",
  "object": "route.completion",
  "created": 1734220800,
  "model": "gpt-5.2-instant",
  "provider": "openai",
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 156,
    "total_tokens": 198
  },
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing is a type of computation..."
      },
      "finish_reason": "stop"
    }
  ],
  "routing": {
    "selected_model": "gpt-5.2-instant",
    "fallback_model": "claude-sonnet-4.5",
    "cache_hit": false,
    "latency_ms": 847,
    "cost_usd": 0.00156
  }
}
GET/v1/models

List all available models with status and pricing information.

{
  "models": [
    {
      "id": "gpt-5.2-thinking",
      "provider": "openai",
      "status": "available",
      "pricing": {"input": 0.01, "output": 0.03},
      "context_window": 128000,
      "capabilities": ["chat", "vision", "function_calling", "reasoning"]
    },
    {
      "id": "claude-opus-4.5",
      "provider": "anthropic",
      "status": "available",
      "pricing": {"input": 0.015, "output": 0.075},
      "context_window": 200000,
      "capabilities": ["chat", "vision", "computer_use", "extended_thinking"]
    },
    {
      "id": "gemini-3-pro",
      "provider": "google",
      "status": "preview",
      "pricing": {"input": 0.00125, "output": 0.005},
      "context_window": 1000000,
      "capabilities": ["chat", "vision", "audio", "video"]
    }
  ]
}

Agent Runtime

POST/v1/agents/run

Execute a multi-step agent task with tool calling, retries, and sandboxed execution.

Request Example

{
  "task": "Research the latest AI news and create a summary report",
  "tools": ["web_search", "read_url", "write_file"],
  "max_steps": 15,
  "timeout_seconds": 300,
  "sandbox": true,
  "callbacks": {
    "on_step": "https://your-webhook.com/agent-step",
    "on_complete": "https://your-webhook.com/agent-complete"
  }
}

Response Example

{
  "id": "agent_run_xyz789",
  "status": "completed",
  "steps": [
    {
      "step": 1,
      "action": "web_search",
      "input": {"query": "latest AI news December 2024"},
      "output": {"results": [...]},
      "duration_ms": 1234
    },
    {
      "step": 2,
      "action": "read_url",
      "input": {"url": "https://..."},
      "output": {"content": "..."},
      "duration_ms": 856
    }
  ],
  "result": {
    "summary": "Here are the key AI developments...",
    "sources": ["https://...", "https://..."]
  },
  "usage": {
    "total_tokens": 4521,
    "total_cost_usd": 0.0892,
    "total_duration_ms": 45678
  }
}

Available Tools

web_search

Web search

read_url

Read URL content

write_file

Write file

code_exec

Execute code

calculator

Calculator

image_gen

Image generation

Analytics & Monitoring

GET/v1/analytics/usage

Get API usage statistics with filtering by time, model, goal, etc.

// Query parameters
?start_date=2024-12-01
&end_date=2024-12-15
&group_by=model
&include_costs=true

// Response
{
  "period": {"start": "2024-12-01", "end": "2024-12-15"},
  "total_requests": 125847,
  "total_tokens": 89234521,
  "total_cost_usd": 1247.56,
  "by_model": {
    "gpt-5.2": {"requests": 45123, "tokens": 34521000, "cost": 521.34},
    "claude-opus-4.5": {"requests": 32456, "tokens": 28900000, "cost": 412.78}
  },
  "cache_stats": {
    "hit_rate": 0.342,
    "savings_usd": 186.23
  }
}

Error Codes

CodeStatusDescription
400Bad RequestInvalid request parameters
401UnauthorizedInvalid or missing API key
429Rate LimitedToo many requests
500Server ErrorInternal server error
503Service UnavailableService temporarily unavailable

Rate Limits

Free

60 req/min

10,000 tokens/min

Pro

500 req/min

100,000 tokens/min

Enterprise

Custom

Contact sales

Ready to get started?

Get your API key and integrate in minutes

Get API KeyView Examples
Previous
Quick Start
Next
Core Concepts

Was this page helpful?

Let us know how we can improve

API Reference | SkyAIApp — SkyAIApp