---
title: "List eval prompt sets"
method: GET
path: "/v1/ai/eval/prompt-sets"
tags: ["AI Eval"]
---

# List eval prompt sets

`GET /v1/ai/eval/prompt-sets`

List eval prompt sets, sorted alphabetically by name. When `model_ids` is omitted, returns prompt sets for every shared model the caller can access. Requires at least the Querier role on each requested model.

## Query parameters

- `archived` 'true' | 'false' — When `true`, returns archived prompt sets instead of active ones. Defaults to `false`.
- `model_ids` string[] — Optional list of model IDs to filter prompt sets by. When omitted, returns prompt sets for every model the caller can access. Supply multiple times to filter by more than one model (e.g., `?model_ids=A&model_ids=B`).

## Response `200`

List of prompt sets, sorted alphabetically by name.

- EvalPromptSetsListResponse
  - `prompt_sets` EvalPromptSetListItem[], required — Prompt sets matching the query, sorted alphabetically by name.
    - `created_at` string, nullable, required — ISO 8601 timestamp when the prompt set was created.
    - `description` string, nullable, required — Optional human-readable description of the prompt set.
    - `id` string, uuid, required — Unique identifier for the prompt set.
    - `is_archived` boolean, required — Whether the prompt set has been archived.
    - `model_id` string, uuid, required — The shared model this prompt set is bound to.
    - `name` string, required — Human-readable name for the prompt set.
    - `slug` string, required — URL-safe identifier for the prompt set. Unique per `model_id`.
    - `updated_at` string, nullable, required — ISO 8601 timestamp when the prompt set was last updated.
    - `latest_run_at` string, nullable, required — ISO 8601 timestamp of the most recent run on this prompt set, if any.
    - `prompt_count` integer, required — Number of prompts in the set.

## Other responses

- `400` — Invalid query params (e.g. `model_ids` contains a non-UUID, or `archived` is not `true`/`false`).
- `401` — Missing or invalid API key.
- `403` — Insufficient permissions. The caller must have at least the Querier role on each requested model.
- `404` — No eval-accessible models for this caller.

---

[API](https://skmtc.net/omni/apis/omni-api.md) · [All operations](https://skmtc.net/omni/apis/omni-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/omni/omni-api/versions/6b02f7349d0e/schema)