PromptDiff

API Reference

GET /v1/evals

List past evaluations or get a specific eval by ID.

GEThttps://promptdiff.bizmarq.com/api/v1/evals
GEThttps://promptdiff.bizmarq.com/api/v1/evals/:id

Parameters

limitnumberoptional

Number of results to return. Default: 20, max: 100.

offsetnumberoptional

Number of results to skip for pagination. Default: 0.

List response

list-response.json
{
  "evals": [
    {
      "eval_id": "eval_01j8abc123",
      "prompt": "What is the capital of France?",
      "models": ["gpt-4o-mini", "claude-haiku-4-5"],
      "created_at": "2026-03-20T10:00:00Z",
      "meta": {
        "total_cost_usd": 0.000031,
        "fastest_model": "gpt-4o-mini"
      }
    }
  ],
  "limit": 20,
  "offset": 0
}

Single eval response

Fetching a specific eval by ID returns the full eval object including all results and metadata.

single-response.json
{
  "eval_id": "eval_01j8abc123",
  "prompt": "What is the capital of France?",
  "models": ["gpt-4o-mini", "claude-haiku-4-5"],
  "results": [
    {
      "model": "gpt-4o-mini",
      "provider": "openai",
      "output": "The capital of France is Paris.",
      "latency_ms": 612,
      "cost_usd": 0.000012,
      "input_tokens": 10,
      "output_tokens": 8,
      "total_tokens": 18
    }
  ],
  "meta": {
    "total_cost_usd": 0.000031,
    "fastest_model": "gpt-4o-mini",
    "cheapest_model": "gpt-4o-mini",
    "created_at": "2026-03-20T10:00:00Z"
  }
}

Example

bash
# List evals
curl "https://promptdiff.bizmarq.com/api/v1/evals?limit=10&offset=0" \
  -H "Authorization: Bearer pd_your_api_key_here"

# Get single eval
curl https://promptdiff.bizmarq.com/api/v1/evals/eval_01j8abc123 \
  -H "Authorization: Bearer pd_your_api_key_here"