API Reference

POST /v1/compare

Run a prompt against multiple LLMs simultaneously and get structured comparison results.

POSThttps://promptdiff.bizmarq.com/api/v1/compare

Request body

promptstringrequired

The prompt to send to each model.

modelsstring[]required

Array of model IDs to compare. Get list from GET /v1/models.

inputstringoptional

Optional input variable to inject into the prompt context.

options.temperaturenumberoptional

Sampling temperature (0-2). Default: 0.7

options.max_tokensnumberoptional

Max output tokens per model. Default: 500

Example

bash

curl -X POST https://promptdiff.bizmarq.com/api/v1/compare \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer pd_your_api_key" \
  -d '{
    "prompt": "Summarize: {input}",
    "input": "The quick brown fox jumps over the lazy dog.",
    "models": ["gpt-4o-mini", "claude-3-haiku", "gemini-1.5-flash"],
    "options": {
      "temperature": 0.3,
      "max_tokens": 200
    }
  }'