Sign in

v1

latestOpenAPI 3.1.02026-07-1320186461.3 KB

Fetch Deployed Prompt

Given a deployment_id, fetches the deployed prompt and its details. Can be optionally used to fill-in the templated prompt with provided inputs.

post/api/parea/v1/deployed-prompt

Request body

deployment_idstring required

ID of deployed prompt

llm_inputsobject nullable

If provided, these key-value pairs will be used to replace the corresponding keys in the templated prompt

Example request

{
  "deployment_id": "p-qZrnFesaeCpqcXJ_yL3wi",
  "llm_inputs": {
    "x": "Python",
    "y": "Flask"
  }
}

Response

Successful Response

deployment_idstring required

This is the ID for a deployed prompt. You can find your deployed prompts on the Deployments tab.

version_numbernumber required

Version number of the deployed prompt

namestring nullable

Name of the deployed prompt

functionsstring[] nullable

If deployed prompt has function, these will appear as JSON strings.

function_callstring nullable

If deployed prompt has a specified function call, it will appear.

modelstring nullable

Model name of deployed prompt

provider'openai' | 'azure' | 'anthropic' | 'anyscale' | 'vertexai' | 'aws_bedrock' | 'openrouter' | 'mistral' | 'litellm' | 'groq' | 'fireworks' | 'cohere'
model_paramsobject nullable

Model parameters of deployed prompt

Example response

{
  "deployment_id": "p-qZrnFesaeCpqcXJ_yL3wi",
  "functions": [],
  "model": "gpt-4o-mini",
  "model_params": {
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "temp": 0.5,
    "top_p": 1
  },
  "name": "hello world",
  "prompt": {
    "inputs": {
      "x": "Python",
      "y": "Flask"
    },
    "messages": [
      {
        "content": "I want a Hello World program in Python. Using the Flask framework.",
        "role": "user"
      }
    ],
    "raw_messages": [
      {
        "content": "I want a Hello World program in {{x}}. Using the {{y}} framework.",
        "role": "user"
      }
    ]
  },
  "provider": "openai",
  "version_number": 1
}