Prompts
Generate API
Deploy your Editor prompts effortlessly with a light and modern package.
Installation
Usage
Simple usage with just a prompt ID
With variables
With Helicone properties
In a chat
Supported Providers and Required Environment Variables
Ensure all required environment variables are correctly defined in your .env
file before making a request.
Always required: HELICONE_API_KEY
Provider | Required Environment Variables |
---|---|
OpenAI | OPENAI_API_KEY |
Azure OpenAI | AZURE_API_KEY , AZURE_ENDPOINT , AZURE_DEPLOYMENT |
Anthropic | ANTHROPIC_API_KEY |
AWS Bedrock | BEDROCK_API_KEY , BEDROCK_REGION |
Google Gemini | GOOGLE_GEMINI_API_KEY |
Google Vertex AI | GOOGLE_VERTEXAI_API_KEY , GOOGLE_VERTEXAI_REGION , GOOGLE_VERTEXAI_PROJECT , GOOGLE_VERTEXAI_LOCATION |
OpenRouter | OPENROUTER_API_KEY |
API Reference
generate(input)
Generates a response using a Helicone prompt.
Parameters
input
(string | object): Either a prompt ID string or a parameters object:promptId
(string): The ID of the prompt to use, created in the Prompt Editorversion
(number | “production”, optional): The version of the prompt to use. Defaults to “production”inputs
(object, optional): Variable inputs to use in the prompt, if anychat
(string[], optional): Chat history for chat-based promptsuserId
(string, optional): User ID for tracking in HeliconesessionId
(string, optional): Session ID for tracking in Helicone Sessionscache
(boolean, optional): Whether to use Helicone’s LLM Caching
Returns
Promise<object>
: The raw response from the LLM provider
Was this page helpful?