Get Prompt Body - Helicone OSS LLM Observability

{ "data": { "model": "gpt-4o-mini", "messages": [ { "role": "system", "content": "You are a helpful AI assistant.\n\nYou are speaking to {{ hc:name:string }}" } ], "temperature": 0.7, "max_tokens": 1000 }, "error": null}

Retrieves the complete prompt body content for a specific prompt version, including messages, model configuration, tools, and other parameters. The prompt body is stored in S3 and contains the actual template content.

Path Parameters#

promptVersionIdstringrequired#

The unique identifier (UUID) of the prompt version to retrieve

Response#

modelstring#

The model specified in the prompt (e.g., "gpt-4o-mini", "claude-3-opus")

messagesarray#

Array of message objects that make up the prompt template

Show Message Object

rolestring#

The role of the message (e.g., "system", "user", "assistant")

contentstring#

The content of the message, may include template variables like {{ hc:variableName:type }}

temperaturenumber#

The temperature setting for the model (if configured)

max_tokensnumber#

The maximum number of tokens to generate (if configured)

toolsarray#

Array of tool/function definitions (if configured)

Notes#

This endpoint returns the full prompt body content, unlike other endpoints that only return metadata
The promptVersionId must be a UUID, not the 6-character prompt ID
Template variables in the format {{ hc:variableName:type }} can be used for dynamic content
Use the /v1/prompt-2025/query/versions endpoint to get the version UUID from a prompt ID