Promptfoo Integration

Promptfoo is an open-source tool for testing and evaluating LLM outputs. It lets you run prompt benchmarks across multiple models and providers, with support for custom OpenAI-compatible endpoints.

Promptfoo supports custom providers in its configuration file.

Prerequisites

An LLM API account with an API key
Promptfoo installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Configure LLM API in Promptfoo

Set environment variables:

export OPENAI_API_KEY="your-llm-api-key-here"
export OPENAI_BASE_URL="https://api.llmapi.ai/v1"

Or configure in promptfooconfig.yaml:

providers:
\- id: openai:openai/gpt-4o
config:
apiKey: your-llm-api-key-here
apiBaseUrl: https://api.llmapi.ai/v1

Run: promptfoo eval

Test the Integration

Verify that Promptfoo can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

Promptfoo lets you compare multiple LLM API models side by side with automated evaluations.

Benefits of Using LLM API with Promptfoo

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

View all available models on the models page.