List Tests | SpeechifyAI API

{
  "next_cursor": "string",
  "has_more": true,
  "tests": [
    {
      "agent_id": "agent_01jqr8x9zg5k2m3n4p5q6r7s8t",
      "config": {
        "context": "The caller says: Hi, I'm Alice.",
        "failure_examples": [
          "Hello! How can I help you?"
        ],
        "success_criteria": "The agent greets Alice by name.",
        "success_examples": [
          "Hi Alice! How can I help you today?"
        ]
      },
      "created_at": "2024-01-15T09:30:00Z",
      "description": "string",
      "id": "test_01ky612y9cb7dbaj638x46msxv",
      "name": "string",
      "type": "reply",
      "updated_at": "2024-01-15T09:30:00Z",
      "folder_id": "folder_01jqr8x9zg5k2m3n4p5q6r7s8t",
      "last_run": {
        "id": "run_01kpvdq02cbtxqqsca60m5scng",
        "test_id": "test_01jqr8x9zg5k2m3n4p5q6r7s8t",
        "agent_id": "agent_01jqr8x9zg5k2m3n4p5q6r7s8t",
        "status": "pending",
        "created_at": "2026-06-24T18:03:11Z",
        "verdict": "passed",
        "started_at": "2026-06-24T18:03:11Z",
        "ended_at": "2026-06-24T18:03:11Z",
        "result": {
          "test_type": "reply",
          "passed": true,
          "rationale": "The agent greeted Alice by name as required.",
          "duration_ms": 1240,
          "reply": {
            "agent_response": "Hi Alice! How can I help you today?",
            "passed": true,
            "rationale": "Response contains the caller's name.",
            "score": 0.95,
            "duration_ms": 1240
          },
          "tool_call": null,
          "simulation": null
        },
        "error": "example"
      },
      "tool_mock_config": {
        "strategy": "selected",
        "no_match_behavior": "call_real_tool",
        "mocks": [
          {
            "tool_name": "get_account_balance",
            "response": null
          }
        ]
      },
      "variables": {}
    }
  ]
}

Workspace-wide list of tests across every agent the caller owns. Supports filters (agent, type, last-run status, folder), full-text search on name/description, and cursor pagination. Each row carries its newest run and attached agent IDs so the list renders without N+1 round-trips. Walk pages while has_more is true.

Authentication

AuthorizationBearer

Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.

Query parameters

agent_idstringOptional

Comma-separated agent IDs to filter on.

typestringOptional

Comma-separated test types (reply|tool|simulation).

statusstringOptional

Comma-separated last-run lifecycle statuses to filter on (pending, running, completed, failed, cancelled).

verdictstringOptional

Comma-separated last-run verdicts to filter on (passed, failed). ANDed with the status filter when both are present.

folder_idstringOptional

Folder ID to filter on, or "root" for unfiled tests.

updated_afterstringOptional

Only return tests updated after this RFC3339 timestamp.

qstringOptional

Substring match on name or description.

limitintegerOptional1-200Defaults to 50

Max items per page (default 50, max 200).

cursorstringOptional

Opaque pagination cursor from a previous response.

Response headers

X-Request-IDstring

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends an X-Request-ID request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify’s server-side logs, and it matches the request_id field in the error envelope.

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends an `X-Request-ID` request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify's server-side logs, and it matches the `request_id` field in the error envelope.

Response

Paginated list.

next_cursorstring or null

Opaque keyset cursor for the next page. Pass back as the cursor request parameter. null when the caller has reached the end of the list (has_more is also false in that case).

has_moreboolean

True when more rows exist beyond this page.

testslist of objects

Errors

401

Unauthorized Error

$	curl https://api.speechify.ai/v1/agents/tests \
>	-H "Authorization: Bearer <token>"

Authentication

Headers

Query parameters

Response headers

Response

Errors