---
title: "Compare Runs"
method: GET
path: "/api/v1/optimization/runs/compare"
tags: ["optimization"]
---

# Compare Runs

`GET /api/v1/optimization/runs/compare`

Compare prompt diffs and scores across optimization runs.

## Query parameters

- `run_ids` string, required — Comma-separated run IDs to compare (max 5).

## Response `200`

Successful Response

- RunComparisonResponse — Cross-run comparison payload.
  - `runs` RunComparisonItem[], required — Compared run summaries.
    - `run_id` string, required — Optimization run identifier.
    - `program_spec` string, required — DSPy program specification optimized.
    - `validation_score` number, nullable — Validation score from the run.
    - `prompt_snapshots` PromptSnapshotItem[], required — Before/after prompt snapshots for this run.
      - `predictor_name` string, required — Predictor name from named_predictors().
      - `prompt_type` string, required — Snapshot type: 'before' or 'after'.
      - `prompt_text` string, required — Full prompt/instruction text.

## Other responses

- `400` — Invalid run_ids parameter.
- `401` — Authentication is required or the provided token is invalid.
- `422` — Validation Error

---

[API](https://skmtc.net/qredence/apis/fleet-rlm.md) · [All operations](https://skmtc.net/qredence/apis/fleet-rlm/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/qredence/fleet-rlm/versions/62e8c152aa18/schema)