{
  "info": {
    "name": "Nscale Serverless Inference API",
    "description": "OpenAI-compatible serverless inference API for Nscale: chat completions, completions, embeddings, image generation, and model discovery at https://inference.api.nscale.com/v1.",
    "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json"
  },
  "auth": {
    "type": "bearer",
    "bearer": [
      {
        "key": "token",
        "value": "{{bearerToken}}",
        "type": "string"
      }
    ]
  },
  "variable": [
    {
      "key": "baseUrl",
      "value": "https://inference.api.nscale.com/v1"
    }
  ],
  "item": [
    {
      "name": "Chat",
      "item": [
        {
          "name": "Create a chat completion",
          "request": {
            "method": "POST",
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "url": {
              "raw": "{{baseUrl}}/chat/completions",
              "host": ["{{baseUrl}}"],
              "path": ["chat", "completions"]
            },
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"meta-llama/Llama-4-Scout-17B-16E-Instruct\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"Hello\" }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 256,\n  \"stream\": false\n}",
              "options": { "raw": { "language": "json" } }
            },
            "description": "Generates a chat completion response for the provided model and chat history. Set stream=true for an SSE token stream."
          }
        }
      ]
    },
    {
      "name": "Completions",
      "item": [
        {
          "name": "Create a completion",
          "request": {
            "method": "POST",
            "header": [
              { "key": "Content-Type", "value": "application/json" }
            ],
            "url": {
              "raw": "{{baseUrl}}/completions",
              "host": ["{{baseUrl}}"],
              "path": ["completions"]
            },
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"meta-llama/Llama-4-Scout-17B-16E-Instruct\",\n  \"prompt\": \"Once upon a time\",\n  \"max_tokens\": 128\n}",
              "options": { "raw": { "language": "json" } }
            },
            "description": "Generates a completion response for the provided model and prompt."
          }
        }
      ]
    },
    {
      "name": "Embeddings",
      "item": [
        {
          "name": "Create embeddings",
          "request": {
            "method": "POST",
            "header": [
              { "key": "Content-Type", "value": "application/json" }
            ],
            "url": {
              "raw": "{{baseUrl}}/embeddings",
              "host": ["{{baseUrl}}"],
              "path": ["embeddings"]
            },
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"Qwen/Qwen3-Embedding-8B\",\n  \"input\": \"The quick brown fox\"\n}",
              "options": { "raw": { "language": "json" } }
            },
            "description": "Returns a vector representation of a given input."
          }
        }
      ]
    },
    {
      "name": "Images",
      "item": [
        {
          "name": "Create an image",
          "request": {
            "method": "POST",
            "header": [
              { "key": "Content-Type", "value": "application/json" }
            ],
            "url": {
              "raw": "{{baseUrl}}/images/generations",
              "host": ["{{baseUrl}}"],
              "path": ["images", "generations"]
            },
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"BlackForestLabs/FLUX.1-schnell\",\n  \"prompt\": \"A serene mountain lake at sunrise\",\n  \"n\": 1,\n  \"size\": \"1024x1024\"\n}",
              "options": { "raw": { "language": "json" } }
            },
            "description": "Creates an image based on the provided text prompt."
          }
        }
      ]
    },
    {
      "name": "Models",
      "item": [
        {
          "name": "List models",
          "request": {
            "method": "GET",
            "header": [],
            "url": {
              "raw": "{{baseUrl}}/models",
              "host": ["{{baseUrl}}"],
              "path": ["models"]
            },
            "description": "Returns a list of serverless models available for inference."
          }
        },
        {
          "name": "Retrieve a model",
          "request": {
            "method": "GET",
            "header": [],
            "url": {
              "raw": "{{baseUrl}}/models/:model",
              "host": ["{{baseUrl}}"],
              "path": ["models", ":model"],
              "variable": [
                { "key": "model", "value": "meta-llama/Llama-4-Scout-17B-16E-Instruct" }
              ]
            },
            "description": "Returns metadata for a single model by identifier."
          }
        }
      ]
    }
  ]
}