> ## Documentation Index > Fetch the complete documentation index at: https://docs.getjumper.io/llms.txt > Use this file to discover all available pages before exploring further. # Drill into one hierarchical summary node > Returns one selected node and its immediate children. Node IDs are local to an analysis, so keep summary_ref on every request. Leaf evidence is included only when requested. ## OpenAPI ````yaml /api-reference/openapi-v1.yaml post /summaries/node openapi: 3.0.3 info: title: Jumper Public API version: '1.0' description: > REST API for third-party integrations with Jumper's media analysis engine. Jumper analyzes video, image, and audio files — enabling semantic visual search, speech transcription, face detection with clustering, and hierarchical summaries. This API exposes those capabilities for use by MAM systems, automation pipelines, and custom tooling. ## Authentication All endpoints except `/health` require a **Jumper Pro** license key. The OpenAPI contract models the supported `X-License-Key` header flow. Jumper also accepts a `license_key` field in many JSON POST bodies as a convenience, but that is a Jumper-specific request-body convention rather than an OpenAPI security scheme. Invalid or missing keys return `401`. Non-Pro keys return `403`. ## Key Concepts - **`cache_dir`** — The folder where Jumper stores analysis data (visual analysis, transcriptions, face clusters). You choose this path. - **`media_paths`** — Absolute filesystem paths to media files. Jumper needs direct access to these files. - **`hash_str`** — A CRC32-based hash that uniquely identifies a media file. Returned by the metadata endpoint. - **`model_key`** — Internal identifier for a visual or speech analysis model variant (e.g. `v2-medium-256`). contact: name: Jumper url: https://getjumper.io servers: - url: http://localhost:6699/api/v1 description: Local Jumper backend security: - HeaderAuth: [] paths: /summaries/node: post: tags: - Summaries summary: Drill into one hierarchical summary node description: >- Returns one selected node and its immediate children. Node IDs are local to an analysis, so keep summary_ref on every request. Leaf evidence is included only when requested. requestBody: required: true content: application/json: schema: type: object required: - cache_dir - node_id properties: cache_dir: type: string summary_ref: type: string description: Preferred stable `:` selector. path: type: string hash_str: type: string analysis_id: type: string node_id: type: string include_evidence: type: boolean default: false responses: '200': description: Compact node and child previews content: application/json: schema: $ref: '#/components/schemas/SummaryReadResponse' '400': description: Invalid cache directory, summary selector, or node ID content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Summary node not found content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: SummaryReadResponse: type: object required: - schema_version - media - summary_ref - analysis_id - node - children properties: schema_version: type: string example: '3' media: type: object required: - hash_str - basename - duration_ms properties: path: type: string nullable: true hash_str: type: string basename: type: string duration_ms: type: integer summary_ref: type: string description: Stable `:` selector. analysis: type: object additionalProperties: true analysis_id: type: string short_summary: type: string root_node_id: type: string transcript_language: type: string nullable: true output_language: type: string output_language_source: type: string enum: - explicit - transcript - default transcript_status: type: string enum: - disabled - not_available - empty - used summary_objective: type: object additionalProperties: true footage_context: type: string nullable: true node: $ref: '#/components/schemas/SummaryNode' children: type: array items: $ref: '#/components/schemas/SummaryNode' additionalProperties: true Error: type: object properties: error: type: string description: Error message required: - error SummaryNode: type: object properties: id: type: string node_type: type: string enum: - leaf - parent start_seconds: type: number end_seconds: type: number child_ids: type: array items: type: string child_count: type: integer named_people: type: array items: type: string search_scope: $ref: '#/components/schemas/FrameRangeMap' verification_hints: type: array description: Bounded evidence limitations with suggested source checks. items: $ref: '#/components/schemas/VerificationHint' summary_text: type: string description: Present for the selected node. summary_preview: type: string description: Bounded preview used for immediate children. evidence: type: object description: >- Present only for a selected leaf when include_evidence is true; contains compact frame, transcript, people, and attribution references. additionalProperties: true FrameRangeMap: type: object additionalProperties: oneOf: - type: array minItems: 2 maxItems: 2 items: type: integer minimum: 0 - type: array items: type: array minItems: 2 maxItems: 2 items: type: integer minimum: 0 description: > Media-path or media-hash keys mapped to half-open `[start_frame, end_frame)` ranges, or lists of ranges, on Jumper's 1 FPS analysis grid. Keys must be inside the selected media scope. VerificationHint: type: object required: - reason_code - claim_category - start_seconds - end_seconds - evidence_ids - suggested_check properties: reason_code: type: string example: speaker_identity_inferred claim_category: type: string example: speaker_identity start_seconds: type: number end_seconds: type: number subject_names: type: array items: type: string basis: type: string evidence_ids: type: array items: type: string suggested_check: type: string enum: - inspect_people_and_transcript_context - read_transcript_range securitySchemes: HeaderAuth: type: apiKey in: header name: X-License-Key description: Jumper Pro license key passed via header ````