{
  "info": {
    "name": "Featherless AI API",
    "description": "OpenAI-compatible REST API for the Featherless AI serverless inference platform. Bearer-authenticated chat completions, text completions, embeddings, and model discovery across thousands of open-weight Hugging Face models.",
    "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json"
  },
  "variable": [
    {
      "key": "baseUrl",
      "value": "https://api.featherless.ai/v1"
    },
    {
      "key": "bearerToken",
      "value": ""
    }
  ],
  "auth": {
    "type": "bearer",
    "bearer": [
      {
        "key": "token",
        "value": "{{bearerToken}}",
        "type": "string"
      }
    ]
  },
  "item": [
    {
      "name": "Chat",
      "item": [
        {
          "name": "Create a chat completion",
          "request": {
            "method": "POST",
            "header": [
              {
                "key": "Content-Type",
                "value": "application/json"
              }
            ],
            "url": {
              "raw": "{{baseUrl}}/chat/completions",
              "host": [
                "{{baseUrl}}"
              ],
              "path": [
                "chat",
                "completions"
              ]
            },
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model\": \"Qwen/Qwen2.5-7B-Instruct\",\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"Hello!\" }\n  ],\n  \"max_tokens\": 1000,\n  \"stream\": false\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            },
            "description": "Generates a model response for a chat conversation. Set stream:true for Server-Sent Events."
          }
        }
      ]
    },
    {
      "name": "Completions",
      "item": [
        {
          "name": "Create a text 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/Meta-Llama-3.1-8B-Instruct\",\n  \"prompt\": \"Your prompt here\",\n  \"max_tokens\": 1000\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            },
            "description": "Generates a text completion for the provided prompt. The prompt may be a string or array of strings (parallel inference)."
          }
        }
      ]
    },
    {
      "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  \"encoding_format\": \"float\"\n}",
              "options": {
                "raw": {
                  "language": "json"
                }
              }
            },
            "description": "Returns vector embeddings for the supplied input using an open embedding model."
          }
        }
      ]
    },
    {
      "name": "Models",
      "item": [
        {
          "name": "List models",
          "request": {
            "method": "GET",
            "header": [],
            "url": {
              "raw": "{{baseUrl}}/models",
              "host": [
                "{{baseUrl}}"
              ],
              "path": [
                "models"
              ]
            },
            "description": "Lists the open-weight models available for serverless inference."
          }
        }
      ]
    }
  ]
}