Model Responses

curl --request POST \
  --url https://{controlPlaneURL}/api/llm/api/inference/openai/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "<string>",
  "messages": [
    {
      "role": "system",
      "content": "<string>"
    }
  ],
  "tools": [
    {
      "type": "<string>",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {}
      }
    }
  ],
  "tool_choice": "none",
  "temperature": 123,
  "top_p": 123,
  "n": 123,
  "stream": true,
  "logprobs": 123,
  "stop": "<string>",
  "max_tokens": 123,
  "presence_penalty": 123,
  "frequency_penalty": 123,
  "logit_bias": {},
  "user": "<string>"
}'

{
  "id": "<string>",
  "object": "<string>",
  "created_at": 123,
  "status": "<string>",
  "error": "<any>",
  "incomplete_details": "<any>",
  "instructions": "<any>",
  "max_output_tokens": 123,
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "type": "<string>",
      "status": "<string>",
      "content": [
        {
          "type": "<string>",
          "annotations": [
            "<any>"
          ],
          "text": "<string>"
        }
      ],
      "role": "<string>"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "reasoning": {
    "effort": "<any>",
    "summary": "<any>"
  },
  "service_tier": "<string>",
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "<string>"
    }
  },
  "tool_choice": "<string>",
  "tools": [
    "<any>"
  ],
  "top_p": 123,
  "truncation": "<string>",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "cached_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "reasoning_tokens": 123
    },
    "total_tokens": 123
  },
  "user": "<any>",
  "metadata": {},
  "provider": "<string>"
}