← modelstatus.ai

API Documentation

Simple REST API to access provider status and incident data

Quick Start

All endpoints are publicly accessible. No authentication required for read-only access.

Base URL:
https://modelstatus.ai
Available Providers
eachlabs
fal
vidu
runway
luma
minimax
black-forest-labs
higgsfield
pixverse
bytedance
kling
google
openai
anthropic

Endpoints

GET
/api/provider/{provider}/status

Get real-time status for a specific provider

Example Request

curl https://modelstatus.ai/api/provider/kling/status

Example Response

{
  "state": "success",
  "result": {
    "provider_username": "kling",
    "provider_name": "Kling",
    "status": "operational",
    "error_rate": 0,
    "average_generation_time": 83.94,
    "timestamp": "2025-10-04T02:06:31.851065"
  }
}
GET
/api/incidents?provider={provider}

Get incident history for a provider

Example Request

curl https://modelstatus.ai/api/incidents?provider=kling

Example Response

{
  "state": "success",
  "result": {
    "incidents": [
      {
        "incident_id": "INC-20251004-035102",
        "title": "Service Degradation Detected",
        "status": "resolved",
        "severity": "critical",
        "detected_at": "2025-10-04T03:51:02"
      }
    ],
    "total": 1
  }
}
GET
/api/incidents/{incidentId}

Get detailed information about a specific incident

Example Request

curl https://modelstatus.ai/api/incidents/INC-20251004-035102

Example Response

{
  "state": "success",
  "result": {
    "incident_id": "INC-20251004-035102",
    "status": "resolved",
    "severity": "critical",
    "error_rate": 102.04,
    "updates": [
      {
        "status": "resolved",
        "message": "Service restored",
        "created_at": "2025-10-04T03:52:06"
      }
    ]
  }
}
Status Values

operational

Provider is functioning normally

degraded

Provider experiencing performance issues

down

Provider is unavailable

insufficient_data

Not enough data to determine status

Rate Limits & Caching

• Provider status endpoints are cached for 30 seconds

• Incident endpoints are cached for 60 seconds

• No rate limits for public read-only access

• Data refreshes automatically on the backend

Built by Eachlabs • Questions? hello@eachlabs.ai