> ## Documentation Index > Fetch the complete documentation index at: https://docs.clavata.ai/llms.txt > Use this file to discover all available pages before exploring further. # List label versions > Lists versions on a label in stable order: `sequential_version` ascending (oldest first), then version ID. Omitting `page_size` uses the default of 100. The maximum `page_size` is 1000. Negative `page_size` is rejected. A label with zero versions returns an empty list. ## OpenAPI ````yaml /openapi.json get /v1/labels/{labelId}/versions openapi: 3.0.0 info: title: Clavata Public API v1 description: Endpoints for creating and managing jobs via the Clavata Public API. version: 1.0.0 contact: name: Clavata.ai url: https://clavata.ai email: support@clavata.ai servers: - url: https://gateway.app.clavata.ai:8443 security: - Bearer_Token: [] tags: - name: Public API description: Endpoints for creating and managing jobs via the Clavata Public API. paths: /v1/labels/{labelId}/versions: get: tags: - Labels summary: List label versions description: >- Lists versions on a label in stable order: `sequential_version` ascending (oldest first), then version ID. Omitting `page_size` uses the default of 100. The maximum `page_size` is 1000. Negative `page_size` is rejected. A label with zero versions returns an empty list. operationId: LabelsService_ListLabelVersions parameters: - name: labelId in: path required: true schema: type: string - name: pageSize description: >- Pagination: maximum number of items to return. When unset or 0, defaults to 100. Maximum 1000. in: query required: false schema: type: integer format: int32 - name: pageToken description: >- Pagination token for keyset pagination (from ListLabelVersions or GetLabel). in: query required: false schema: type: string responses: '200': description: A successful response. content: application/json: schema: $ref: '#/components/schemas/v1ListLabelVersionsResponse' default: description: An unexpected error response. content: application/json: schema: $ref: '#/components/schemas/rpcStatus' components: schemas: v1ListLabelVersionsResponse: type: object properties: labelVersions: type: array items: $ref: '#/components/schemas/v1LabelVersion' nextPageToken: type: string description: Set when more versions remain after this page. rpcStatus: type: object properties: code: type: integer format: int32 message: type: string details: type: array items: $ref: '#/components/schemas/protobufAny' v1LabelVersion: type: object properties: labelVersionId: type: string title: The label version ID as set in the database labelId: type: string title: The label ID this version belongs to text: type: string title: The single-label DSL text for this version blob: type: string format: byte title: >- Optional compiled representation blob (typically omitted from customer-facing responses) description: type: string title: Optional description for this version signalCount: type: integer format: int64 title: Number of signals in this version (complexity metric) totalSignalTokens: type: integer format: int64 title: Total signal tokens in this version (complexity metric) created: type: string format: date-time title: Time the version was created expunged: type: boolean title: If the version is soft-deleted, this is set to true createdById: type: string title: The user ID who created this version sequentialVersion: type: integer format: int32 title: Sequential version number (v1=1, v2=2, etc.) based on creation order parentLabelVersionId: type: string title: >- The parent version this was created from/based on (nil for first version or when lineage is unknown) complexityScore: type: number format: float title: Complexity score of the label version labelEvalOptions: $ref: '#/components/schemas/v1LabelEvalOptions' globalContext: type: string description: >- Optional global context to inject into LLM context window during evaluation. This provides additional context about the nature of content being evaluated. tokenCountsV2: $ref: '#/components/schemas/v1TokenCountsV2' description: >- LabelVersion is an immutable snapshot of a label's DSL + compiled representation. protobufAny: type: object properties: '@type': type: string additionalProperties: {} v1LabelEvalOptions: type: object properties: bypassCache: type: boolean title: Whether to bypass the query cache during evaluation expedited: type: boolean title: Whether to use expedited evaluation (prioritizing speed over cost) bundleSize: type: integer format: int64 title: The bundle size to use for query batching in Hermes threshold: type: number format: double title: The threshold to use for determining truthiness stack: type: string title: >- The stack name to use for evaluation (overrides default stack in Hermes) imageDetailLevel: $ref: '#/components/schemas/v1ImageDetailLevel' description: >- LabelEvalOptions are options that can be set per-label to control evaluation behavior. Field numbers/types intentionally mirror PolicyEvalOptions for parity. v1TokenCountsV2: type: object properties: dslTokenCount: type: integer format: int64 description: V2 DSL-only token count for display. globalContextTokens: type: integer format: int64 description: V2 token count for the saved global context. signalTokens: type: integer format: int64 description: V2 token count for formatted DSL signals. signalSpecialTokens: type: integer format: int64 description: V2 token count for DSL prompt special/structural tokens. contentSpecialTokens: type: integer format: int64 description: V2 token count for content prompt special/structural tokens. description: >- TokenCountsV2 groups the static V2 token counts saved alongside a policy version, label version, or user label draft. The counts are calculated together, so message presence signals that V2 accounting is available for the saved DSL. v1ImageDetailLevel: type: string enum: - IMAGE_DETAIL_LEVEL_UNSPECIFIED - IMAGE_DETAIL_LEVEL_VERY_LOW - IMAGE_DETAIL_LEVEL_LOW - IMAGE_DETAIL_LEVEL_MEDIUM - IMAGE_DETAIL_LEVEL_HIGH - IMAGE_DETAIL_LEVEL_VERY_HIGH default: IMAGE_DETAIL_LEVEL_UNSPECIFIED description: >- ImageDetailLevel selects how much image detail is preserved when images are evaluated. Levels are semantic; the selected extractor's vision encoder maps each level to a model-specific token budget. Unspecified preserves the extractor's configured default. securitySchemes: Bearer_Token: type: http scheme: bearer bearerFormat: JWT ````