Prompt Render

curl -X POST "https://api.portkey.ai/v1/prompts/YOUR_PROMPT_ID/render" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "variables": {
      "user_input": "Hello world"
    },
    "max_tokens": 250,
    "presence_penalty": 0.2
  }'

{
  "success": true,
  "data": {
    "messages": [
      {
        "content": "<string>",
        "role": "system",
        "name": "<string>"
      }
    ],
    "model": "gpt-4-turbo",
    "frequency_penalty": 0,
    "logit_bias": null,
    "logprobs": false,
    "top_logprobs": 10,
    "max_tokens": 123,
    "n": 1,
    "presence_penalty": 0,
    "response_format": {
      "type": "text"
    },
    "seed": 0,
    "stop": "<string>",
    "stream": false,
    "stream_options": null,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 2030
    },
    "temperature": 1,
    "top_p": 1,
    "tools": [
      {
        "type": "function",
        "function": {
          "description": "<string>",
          "name": "<string>",
          "parameters": {},
          "strict": false
        }
      }
    ],
    "tool_choice": "none",
    "parallel_tool_calls": true,
    "user": "user-1234",
    "function_call": "none",
    "functions": [
      {
        "description": "<string>",
        "name": "<string>",
        "parameters": {}
      }
    ]
  }
}

POST

prompts

{promptId}

render

curl -X POST "https://api.portkey.ai/v1/prompts/YOUR_PROMPT_ID/render" \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -d '{
    "variables": {
      "user_input": "Hello world"
    },
    "max_tokens": 250,
    "presence_penalty": 0.2
  }'

{
  "success": true,
  "data": {
    "messages": [
      {
        "content": "<string>",
        "role": "system",
        "name": "<string>"
      }
    ],
    "model": "gpt-4-turbo",
    "frequency_penalty": 0,
    "logit_bias": null,
    "logprobs": false,
    "top_logprobs": 10,
    "max_tokens": 123,
    "n": 1,
    "presence_penalty": 0,
    "response_format": {
      "type": "text"
    },
    "seed": 0,
    "stop": "<string>",
    "stream": false,
    "stream_options": null,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 2030
    },
    "temperature": 1,
    "top_p": 1,
    "tools": [
      {
        "type": "function",
        "function": {
          "description": "<string>",
          "name": "<string>",
          "parameters": {},
          "strict": false
        }
      }
    ],
    "tool_choice": "none",
    "parallel_tool_calls": true,
    "user": "user-1234",
    "function_call": "none",
    "functions": [
      {
        "description": "<string>",
        "name": "<string>",
        "parameters": {}
      }
    ]
  }
}

Given a prompt ID, variable values, and optionally any hyperparameters, this API returns a JSON object containing the raw prompt template.

Note: Unlike inference requests, Prompt Render API calls are processed through Portkey’s Control Plane services.

Example: Using Prompt Render output in a new request

Here’s how you can take the output from the render API and use it for making a separate LLM call. We’ll take example of OpenAI SDKs, but you can use it simlarly for any other frameworks like Langchain etc. as well.

from portkey_ai import Portkey
from openai import OpenAI

# Retrieving the Prompt from Portkey

portkey = Portkey(
  api_key="PORTKEY_API_KEY"
)

render_response = portkey.prompts.render(
  prompt_id="PROMPT_ID",
  variables={ "movie":"Dune 2" }
)

PROMPT_TEMPLATE = render_response.data

# Making a Call to OpenAI with the Retrieved Prompt

openai = OpenAI(
    api_key = "OPENAI_API_KEY",
    base_url = "https://api.portkey.ai/v1",
    default_headers = {
      'x-portkey-provider': 'openai',
      'x-portkey-api-key': 'PORTKEY_API_KEY',
      'Content-Type': 'application/json',
    }
)

chat_complete = openai.chat.completions.create(**PROMPT_TEMPLATE)

print(chat_complete.choices[0].message.content)

Authorizations

x-portkey-api-key

string

header

required

Path Parameters

promptId

string

required

The unique identifier of the prompt template to render

Body

application/json

Note: Although hyperparameters are shown grouped here (like messages, max_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'.

variables

object

required

Variables to substitute in the prompt template

hyperparameters

object

Note: All hyperparameters are optional. Pass them at the root level, and not nested under hyperparameters. Their grouping here is for educational purposes only.

Show child attributes

Response

200 - application/json

Successful rendered prompt

success

boolean

required

Indicates if the render was successful

data

object

required

Show child attributes

Prompt Completions Insert a Log

API Reference

SDK

Chat Completions

Responses

Portkey Endpoints

Embeddings

Images

Models

Audio

Other APIs

Completions

Moderations

Fine-tuning

Batch

Files

Assistants

Authorizations

Path Parameters

Body

Response