{
  "item": [
    {
      "id": "a1f0c2d4-1111-4a11-9c01-000000000001",
      "name": "Inference",
      "description": {
        "content": "",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000010",
          "name": "Invoke a deployed function",
          "request": {
            "name": "Invoke a deployed function",
            "description": {
              "content": "Calls a deployed Cortex function. The JSON body maps to the function parameters. Returns run_id, run_time_ms, and result.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/{{functionName}}",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "{{functionName}}"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"<string>\"\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        },
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000011",
          "name": "Invoke run function",
          "request": {
            "name": "Invoke run function",
            "description": {
              "content": "Calls the run function on a deployed app.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/run",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "run"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"<string>\"\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        }
      ],
      "event": []
    },
    {
      "id": "a1f0c2d4-1111-4a11-9c01-000000000002",
      "name": "Streaming",
      "description": {
        "content": "",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000020",
          "name": "Stream function output (SSE)",
          "request": {
            "name": "Stream function output (SSE)",
            "description": {
              "content": "Streams live model output over a Server-Sent Events (text/event-stream) response from a generator function.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/run",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "run"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              },
              {
                "key": "Accept",
                "value": "text/event-stream"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"upper_range\": 3\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        }
      ],
      "event": []
    },
    {
      "id": "a1f0c2d4-1111-4a11-9c01-000000000003",
      "name": "Async",
      "description": {
        "content": "",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000030",
          "name": "Submit async run",
          "request": {
            "name": "Submit async run",
            "description": {
              "content": "Submits the function for asynchronous execution. Returns 202 Accepted with a run_id; results are forwarded to a configured webhookEndpoint.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/run?async=true",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "run"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [
                {
                  "key": "async",
                  "value": "true"
                }
              ],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"<string>\"\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        }
      ],
      "event": []
    },
    {
      "id": "a1f0c2d4-1111-4a11-9c01-000000000004",
      "name": "OpenAI Compatible",
      "description": {
        "content": "",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000040",
          "name": "Chat completions",
          "request": {
            "name": "Chat completions",
            "description": {
              "content": "OpenAI-compatible chat completions served by a deployed function.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/{{functionName}}/chat/completions",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "{{functionName}}",
                "chat",
                "completions"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"<string>\"\n    }\n  ]\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        },
        {
          "id": "a1f0c2d4-1111-4a11-9c01-000000000041",
          "name": "Embeddings",
          "request": {
            "name": "Embeddings",
            "description": {
              "content": "OpenAI-compatible embeddings served by a deployed function.",
              "type": "text/plain"
            },
            "url": {
              "raw": "{{baseUrl}}/v4/{{projectId}}/{{appName}}/{{functionName}}/embedding",
              "path": [
                "v4",
                "{{projectId}}",
                "{{appName}}",
                "{{functionName}}",
                "embedding"
              ],
              "host": [
                "{{baseUrl}}"
              ],
              "query": [],
              "variable": []
            },
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "method": "POST",
            "auth": null,
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"<string>\",\n  \"input\": \"<string>\"\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            }
          },
          "response": []
        }
      ],
      "event": []
    }
  ],
  "event": [],
  "variable": [
    {
      "type": "string",
      "value": "https://api.aws.us-east-1.cerebrium.ai",
      "key": "baseUrl"
    },
    {
      "type": "string",
      "value": "p-xxxxxxxx",
      "key": "projectId"
    },
    {
      "type": "string",
      "value": "my-app",
      "key": "appName"
    },
    {
      "type": "string",
      "value": "run",
      "key": "functionName"
    }
  ],
  "auth": {
    "type": "bearer",
    "bearer": [
      {
        "key": "token",
        "value": "{{bearerToken}}"
      }
    ]
  },
  "info": {
    "_postman_id": "5351e0d3-d283-4104-bd01-cerebrium0001",
    "name": "Cerebrium Cortex Inference API",
    "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json",
    "description": {
      "content": "Specification of the Cerebrium serverless GPU inference surface. Each deployed Cortex function is an authenticated POST endpoint at /v4/{project}/{app}/{function}.\n\nContact Support:\n Name: Cerebrium Support\n Email: support@cerebrium.ai",
      "type": "text/plain"
    }
  }
}