> ## Documentation Index > Fetch the complete documentation index at: https://docs.veri.studio/llms.txt > Use this file to discover all available pages before exploring further. # Archive an annotation queue > Soft delete: the queue takes no new items or reservations and leaves the default list. Its items and scores are kept, and the name stays reserved. Idempotent. ## OpenAPI ````yaml /api-reference/openapi.json delete /v1/annotation-queues/{id_or_name} openapi: 3.1.0 info: title: Veri API description: >- REST API for the Veri RL post-training platform. All requests require a Bearer API key (`vk_` prefix). license: name: '' version: 0.1.0 servers: - url: https://api.veri.studio description: Production security: [] tags: - name: Training jobs description: Create, monitor, and manage training jobs. - name: Datasets description: Upload and connect training datasets. - name: Deployments description: Serve trained models and run inference. - name: Volumes description: Persistent file storage mounted into jobs. - name: Models description: Custom model registry deployments serve from. - name: Regions description: Discover available launch regions. - name: GPU description: Live GPU availability by provider and region. - name: Code artifacts description: Upload custom training script bundles. - name: Billing description: Credit balance and transaction history. - name: API keys description: Create and revoke API keys. - name: Account description: The authenticated caller's identity. - name: Settings description: Account-level integrations (Weights & Biases). - name: Metrics description: Prometheus metrics export for your own observability stack. - name: Evaluators description: 'Evaluators: versioned scoring rules (LLM judge, code, human).' - name: Experiments description: >- Experiments: offline runs of a pinned dataset snapshot through a target, scored by pinned evaluators. - name: Annotation queues description: >- Human review: queue traces, threads and experiment items, reserve one at a time, score them and feed corrections back into datasets. - name: Monitors description: >- Monitors: evaluators scoring a sampled share of a deployment's live traffic. - name: Observability description: Agent conversations, agents and their traffic. - name: Public runs description: Unauthenticated reads of runs their owners published to Explore. paths: /v1/annotation-queues/{id_or_name}: delete: tags: - Annotation queues summary: Archive an annotation queue description: >- Soft delete: the queue takes no new items or reservations and leaves the default list. Its items and scores are kept, and the name stays reserved. Idempotent. operationId: archive parameters: - name: id_or_name in: path description: Queue id (aq_...) or name required: true schema: type: string responses: '200': description: The archived queue content: application/json: schema: $ref: '#/components/schemas/QueueResponse' '400': description: Evals disabled '404': description: No such queue in the caller's workspace security: - bearerAuth: [] components: schemas: QueueResponse: type: object required: - object - id - name - target_type - evaluators - reservation_minutes - counts - created_at - updated_at properties: object: type: string description: Always "annotation_queue". id: type: string description: '`aq_...`' name: type: string description: type: - string - 'null' instructions: type: - string - 'null' target_type: type: string description: trace | thread | experiment_item evaluators: type: array items: $ref: '#/components/schemas/QueuePin' description: The pinned evaluator versions. reservation_minutes: type: integer format: int32 counts: $ref: '#/components/schemas/QueueCounts' description: Items per status; an expired reservation counts as pending. archived_at: type: - string - 'null' format: date-time description: 'Set when archived: no new items or reservations.' created_by: type: - string - 'null' created_at: type: string format: date-time updated_at: type: string format: date-time evaluator_specs: type: - array - 'null' items: $ref: '#/components/schemas/QueueEvaluator' description: |- The pinned versions in full. Only on GET /v1/annotation-queues/{id_or_name}. QueuePin: type: object description: |- One pinned evaluator version, with the facts a reviewer UI lists (all immutable: versions never change and evaluators are never renamed). required: - evaluator_id - version - name - method - scope - output_type properties: evaluator_id: type: string version: type: integer format: int32 name: type: string method: type: string description: llm_judge | code | human scope: type: string description: single_turn | thread output_type: type: string description: boolean | categorical | numeric QueueCounts: type: object description: Items per effective status. An expired reservation counts as pending. required: - pending - reserved - completed - skipped properties: pending: type: integer format: int64 reserved: type: integer format: int64 completed: type: integer format: int64 skipped: type: integer format: int64 QueueEvaluator: type: object description: A pinned evaluator version, as a reviewer scores it. required: - evaluator_id - name - version - method - scope - output_type - output_config properties: evaluator_id: type: string name: type: string description: type: - string - 'null' version: type: integer format: int32 method: type: string description: llm_judge | code | human scope: type: string description: single_turn | thread output_type: type: string description: boolean | categorical | numeric output_config: type: object description: >- boolean {pass_when}, categorical {labels, pass_labels}, numeric {min, max, pass_threshold, higher_is_better}: the values a score may take. instructions: type: - string - 'null' description: 'Human evaluators: the version''s reviewer instructions.' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API key description: API key with the `vk_` prefix. Create one from the dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.