Create Structured Output

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. Create a completion for the provided prompt and parameters Official Documentation: https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses

Endpoint

POST http://v98store.com/v1/chat/completions

cURL Command

curl -X POST 'http://v98store.com/v1/chat/completions' \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer YOUR_TOKEN' \ -d '{ "model": "gpt-4.1-2025-04-14", "messages": [ { "role": "system", "content": "Determine if the user input violates specific guidelines and explain if they do." }, { "role": "user", "content": "How do I prepare for a job interview?" } ], "response_format": { "type": "json_schema", "json_schema": { "name": "content_compliance", "description": "Determines if content is violating specific moderation rules", "schema": { "type": "object", "properties": { "is_violating": { "type": "boolean", "description": "Indicates if the content is violating guidelines" }, "category": { "type": [ "string", "null" ], "description": "Type of violation, if the content is violating guidelines. Null otherwise.", "enum": [ "violence", "sexual", "self_harm" ] }, "explanation_if_violating": { "type": [ "string", "null" ], "description": "Explanation of why the content is violating" } }, "required": [ "is_violating", "category", "explanation_if_violating" ], "additionalProperties": false }, "strict": true } } }'

Parameters

Request Body

Example

{
  "model": "gpt-4.1-2025-04-14",
  "messages": [
    {
      "role": "system",
      "content": "Determine if the user input violates specific guidelines and explain if they do."
    },
    {
      "role": "user",
      "content": "How do I prepare for a job interview?"
    }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "content_compliance",
      "description": "Determines if content is violating specific moderation rules",
      "schema": {
        "type": "object",
        "properties": {
          "is_violating": {
            "type": "boolean",
            "description": "Indicates if the content is violating guidelines"
          },
          "category": {
            "type": [
              "string",
              "null"
            ],
            "description": "Type of violation, if the content is violating guidelines. Null otherwise.",
            "enum": [
              "violence",
              "sexual",
              "self_harm"
            ]
          },
          "explanation_if_violating": {
            "type": [
              "string",
              "null"
            ],
            "description": "Explanation of why the content is violating"
          }
        },
        "required": [
          "is_violating",
          "category",
          "explanation_if_violating"
        ],
        "additionalProperties": false
      },
      "strict": true
    }
  }
}

Responses

200 -

Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}