{
  "opencollection": "1.0.0",
  "info": {
    "name": "Nscale Serverless Inference API",
    "version": "1.0"
  },
  "request": {
    "auth": {
      "type": "bearer",
      "token": "{{bearerToken}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Chat",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Create a chat completion",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.api.nscale.com/v1/chat/completions",
            "body": {
              "type": "json",
              "data": "{\n  \"model\": \"meta-llama/Llama-4-Scout-17B-16E-Instruct\",\n  \"messages\": [{ \"role\": \"user\", \"content\": \"Hello\" }],\n  \"stream\": false\n}"
            }
          },
          "docs": "Generates a chat completion response for the provided model and chat history. Set stream=true for an SSE token stream."
        }
      ]
    },
    {
      "info": {
        "name": "Completions",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Create a completion",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.api.nscale.com/v1/completions",
            "body": {
              "type": "json",
              "data": "{\n  \"model\": \"meta-llama/Llama-4-Scout-17B-16E-Instruct\",\n  \"prompt\": \"Once upon a time\",\n  \"max_tokens\": 128\n}"
            }
          },
          "docs": "Generates a completion response for the provided model and prompt."
        }
      ]
    },
    {
      "info": {
        "name": "Embeddings",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Create embeddings",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.api.nscale.com/v1/embeddings",
            "body": {
              "type": "json",
              "data": "{\n  \"model\": \"Qwen/Qwen3-Embedding-8B\",\n  \"input\": \"The quick brown fox\"\n}"
            }
          },
          "docs": "Returns a vector representation of a given input."
        }
      ]
    },
    {
      "info": {
        "name": "Images",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Create an image",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.api.nscale.com/v1/images/generations",
            "body": {
              "type": "json",
              "data": "{\n  \"model\": \"BlackForestLabs/FLUX.1-schnell\",\n  \"prompt\": \"A serene mountain lake at sunrise\",\n  \"n\": 1,\n  \"size\": \"1024x1024\"\n}"
            }
          },
          "docs": "Creates an image based on the provided text prompt."
        }
      ]
    },
    {
      "info": {
        "name": "Models",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "List models",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.api.nscale.com/v1/models"
          },
          "docs": "Returns a list of serverless models available for inference."
        },
        {
          "info": {
            "name": "Retrieve a model",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.api.nscale.com/v1/models/{model}"
          },
          "docs": "Returns metadata for a single model by identifier."
        }
      ]
    }
  ]
}