---
title: "List runs for deployment"
method: GET
path: "/v1/projects/{project_id}/deployments/{deployment_id}/runs"
tags: ["runs"]
---

# List runs for deployment

`GET /v1/projects/{project_id}/deployments/{deployment_id}/runs`

## Request

- Base URL: `https://api.connic.co`
- URL: `https://api.connic.co/v1/projects/{project_id}/deployments/{deployment_id}/runs`
- Auth: HTTP bearer

Paginated runs created by this deployment, newest first. Items have the same shape as `GET /runs`.

Required permission: `runs.view`.

## Path parameters

- `project_id` string, uuid, required
- `deployment_id` string, uuid, required

## Query parameters

- `limit` integer: Page size, 1 to 250.
- `offset` integer: Number of runs to skip.
- `convert_costs_to` 'EUR' | 'USD', nullable: Convert token costs to EUR or USD at the daily ECB reference rate of each model call

## Response `200`

Successful Response

- PublicRunListResponse
  - `runs` PublicRunListItemResponse[], required: Runs on this page.
    - `id` string, uuid, required
    - `deployment_id` string, uuid, nullable, required: Deployment that ran the agent. Null when none is recorded.
    - `agent_name` string, required: Agent the run belongs to.
    - `test_name` string, nullable, required: A/B test variant that handled the run. Null for the base agent.
    - `status` 'scheduled' | 'queued' | 'started' | 'awaiting_approval' | 'completed' | 'failed' | 'cancelled' | 'blocked', required: Run state: `scheduled` until its start time, `queued`, `started` while executing, `awaiting_approval` while paused for a human decision, then `completed`, `failed` or `cancelled`.
    - `queued_at` string, date-time, nullable, required: When the run entered the queue.
    - `started_at` string, date-time, nullable, required: When execution began. Null while the run is scheduled or queued.
    - `ended_at` string, date-time, nullable, required: When the run finished. Null while it is still active.
    - `duration_ms` number, nullable, required: Execution time in milliseconds, excluding time spent waiting for approvals or child runs. Null until the run ends.
    - `data_deleted_at` string, date-time, nullable, required: When the run was deleted. Its input, output, error and traces are removed; status, timing and usage remain.
    - `can_delete_data` boolean, required: Whether the run can be deleted now: it and its background processing have finished and it is not deleted yet.
    - `token_usage` PublicTokenUsageResponse, required: Token counts summed over model calls.
      - `input_tokens` integer, required: Prompt tokens sent to the model, including cached tokens.
      - `output_tokens` integer, required: Tokens the model generated, excluding thinking tokens.
      - `cached_input_tokens` integer, required: Part of `input_tokens` read from the provider's prompt cache.
      - `thinking_tokens` integer, required: Reasoning tokens the model generated.
      - `total_tokens` integer, required: Input, output and thinking tokens combined.
      - `audio_input_tokens` integer: Part of `input_tokens` that was audio.
      - `audio_output_tokens` integer: Part of `output_tokens` that was audio.
      - `audio_cached_input_tokens` integer: Part of `cached_input_tokens` that was audio.
      - `audio_thinking_tokens` integer: Part of `thinking_tokens` that was audio.
      - `audio_usage_missing` boolean: True when at least one model call did not report its audio breakdown, so audio counts may be too low.
    - `token_cost` PublicTokenCostResponse, required: Token cost in each model's pricing currency, or in one currency when `convert_costs_to` is set.
      - `amounts` object, required: Total cost keyed by currency code (`EUR` or `USD`), as a decimal string with 12 decimal places. Only currencies with a nonzero amount are included.
      - `breakdown` object, required: Cost split by token type and by agent versus judge, keyed by currency code.
      - `coverage` PublicTokenCostCoverageResponse, required: How many model calls could be priced.
        - `complete` boolean, required: True when every model call could be priced.
        - `call_count` integer, required: Model calls covered by the report.
        - `priced_call_count` integer, required: Calls included in the cost amounts.
        - `unpriced_call_count` integer, required: Calls without a known price or without reported token usage. They are left out of the amounts.
        - `unpriced_models` string[], required: Models of the unpriced calls.
      - `converted_to` string, nullable: Currency the amounts were converted to at the daily ECB reference rate of each call. Present only when `convert_costs_to` is set.
      - `native_amounts` object, nullable: Totals in each model's pricing currency before conversion, as decimal strings keyed by currency code. Present only when `convert_costs_to` is set.
    - `scheduled_at` string, date-time, nullable, required: Time the run is scheduled to start. Null for runs that were not scheduled.
    - `guardrail_interventions` PublicGuardrailInterventionResponse[], required: Guardrail rules that warned, blocked or redacted content during the run.
      - `id` string, nullable
      - `name` string, nullable: Name of the custom guardrail. Null for built-in types.
      - `type` string, nullable: Guardrail type, such as `prompt_injection`, `pii`, `moderation`, `topic_restriction`, `regex` or `custom`.
      - `direction` string, nullable: `input` when the rule checked the run input, `output` when it checked the agent output.
      - `mode` string, nullable: Action configured for the rule: `block`, `warn` or `redact`.
      - `status` 'warned' | 'blocked' | 'redacted', required: Outcome: `warned` let the content through with a warning, `blocked` stopped it, `redacted` removed the matched content.
      - `message` string, nullable: Explanation from the guardrail. Empty after the run is deleted.
    - `connector_id` string, uuid, nullable: Connector that triggered the run. Null for other triggers; omitted with `projection=summary`.
    - `ab_test_ids` string[]: A/B tests the run was assigned to. Omitted with `projection=summary`.
    - `input` string, nullable: Input payload of the run. Null after the run is deleted; omitted with `projection=summary`.
    - `output` string, nullable: Final agent output. Null until the run completes or after it is deleted; omitted with `projection=summary`.
    - `error` string, nullable: Error message for runs that did not complete. Null otherwise; omitted with `projection=summary`.
    - `triggered_by` string, nullable: ID of the parent run when another agent started this run. Null otherwise; omitted with `projection=summary`.
  - `total` integer, nullable, required: Runs matching the filters across all pages. Null when `include_total=false`.
  - `limit` integer, required: Page size used.
  - `offset` integer, required: Number of runs skipped.

## Other responses

- `401`: Missing or invalid API key.
- `403`: The API key lacks the required permission or access to the environment.
- `404`: The resource does not exist in this project.
- `422`: Validation Error
- `429`: Rate limit exceeded.

---

[API](https://skmtc.dev/connic/apis/connic-api.md) · [All operations](https://skmtc.dev/connic/apis/connic-api/llms.txt) · [OpenAPI document](https://skmtc.dev/connic/apis/connic-api/revisions/482932da5fbe?raw)