用于生产的 AI 基础设施

在付费之前测试您的 AI 工作流。.

  • Free 永久 up to 25,000 每月请求数
  • No credit card required
  • Free 测试模式
$ curl https://api.modelriver.com/v1/ai/async \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "workflow": "book_review",
    "messages": [{"role": "user", "content": "Hello!"}],
    "user_id": "user_12345",
    "task_id": "task_67890"
  }'
实时请求处理

通过以下功能观察请求流向:
智能路由和自动故障转移。.

Toggle to dark mode
Live Logs
Waiting for requests...
统一 API 网关

简单的集成 只需一个端点和一个 API 密钥

REQUEST
{
  "workflow": "my_book_task",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "user_id": "user_12345",
  "task_id": "task_67890"
}
IN PROGRESS
{
  "message": "success",
  "status": "pending",
  "channel_id": "a1b2c3d4-...",
  "ws_token": "one-time-websocket-token",
  "websocket_url": "wss://api.modelriver.com/socket",
  "websocket_channel": "ai_response:PROJECT_ID:a1b2c3d4-..."
}
SUCCESS
{
  "message": "success",
  "status": "success",
  "data": {
    "response": "Hello! How can I help?",
    "intent": "greeting",
    "confidence": 0.95
  },
  "model": "gpt-5.2",
  "customer_data": {
    "user_id": "user_12345",
    "task_id": "task_67890"
  },
  "meta": {
    "duration_ms": 1250,
    "usage": {
      "prompt_tokens": 21,
      "completion_tokens": 42,
      "total_tokens": 63
    }
  }
}
集成测试

在发布前测试 ,通过免费的 Playground 发现问题。.

安全测试模式 运行方式与生产环境一致,且不影响实际用户。.

免费 Playground 提供无限次数的免费测试请求。.

验证输出 让您在上线前验证响应格式。.

测试模式

与生产环境相同的设置,安全的沙箱。.

实时配置
mode "测试"
structure "todo_struct"
故障转移 enabled
rate_limits 30-300/min per IP,
40-1,000/min per project
成本 free

响应预览

准确查看您的应用程序将收到的内容。.

// sample response data
{
  "data": {
    "todo": {
      "id": 1,
      "title": "Finish project proposal",
      "description": "Complete the first draft and review key points",
      "completed": false,
      "priority": "high"
    }
  }
}
免费 Playground 测试

准备好测试您的工作流了吗?
而无需烧掉额度??

免费开始。包含 25k 次请求。.