> ## Documentation Index > Fetch the complete documentation index at: https://docs.spyglass.so/llms.txt > Use this file to discover all available pages before exploring further. # Get a brand's ad creatives > Return creatives for a brand. `mode: "structured"` derives filters from `userRequest`; `mode: "smart"` also runs a semantic search. Limited to 120 requests per minute for this endpoint. Costs 1,000 microdollars ($0.0010) per creative returned, charged against your plan's monthly credits. The count field is what you were charged for. Both modes run a language model, so the call bills a minimum of one row even when nothing matches. In that case `count` is 0 but you are charged for one row. ## OpenAPI ````yaml https://app.spyglass.so/api/v1/openapi.json post /brands/{id}/media openapi: 3.1.0 info: title: Spyglass API version: 1.0.0 description: |- Query Spyglass ad intelligence over HTTP. ## Authentication Send your key as a bearer token: `Authorization: Bearer sg_live_...`. Create and revoke keys in Settings → API. A key is scoped to the team it was created for, and stops working if you leave that team. ## Billing Calls draw on the same monthly credits as the rest of Spyglass. Most endpoints charge per row returned. Bound what a call costs with `limit` on /brands/{id}/media, /insights and /landing-pages, and with `count` on /brands/search. POST /brands/index and GET /brands/{id}/index-status are free and are not blocked when the team is out of credits. Requests that fail validation, auth, or the credit check are never charged. Calls that run a language model — /brands/{id}/media in either mode, and /brands/search with `mode: "smart"` — are charged a minimum of one row even when nothing matches, because the model ran either way. ## Rate limits Three limits apply: 60 requests per minute per IP address, 120 per minute per API key, and a per-endpoint limit listed on each operation. Whichever is lowest applies. Exceeding any of them returns 429 with a Retry-After header. servers: - url: https://app.spyglass.so/api/v1 security: - bearerAuth: [] tags: - name: Lookup description: Find a brand you already know about. - name: Indexing description: Add a brand we do not have yet, then poll until ready. - name: Ads description: Creatives, insights, and landing pages for a brand. paths: /brands/{id}/media: post: tags: - Ads summary: Get a brand's ad creatives description: >- Return creatives for a brand. `mode: "structured"` derives filters from `userRequest`; `mode: "smart"` also runs a semantic search. Limited to 120 requests per minute for this endpoint. Costs 1,000 microdollars ($0.0010) per creative returned, charged against your plan's monthly credits. The count field is what you were charged for. Both modes run a language model, so the call bills a minimum of one row even when nothing matches. In that case `count` is 0 but you are charged for one row. operationId: getBrandMedia parameters: - name: id in: path required: true description: Brand id returned by POST /brands/search. schema: type: string requestBody: required: true content: application/json: schema: type: object properties: mode: type: string enum: - structured - smart userRequest: type: string minLength: 1 maxLength: 2000 limit: default: 100 type: integer minimum: 1 maximum: 2000 required: - mode - userRequest example: mode: smart userRequest: video ads about comfort limit: 20 responses: '200': description: Matching creatives. content: application/json: schema: type: object properties: count: type: integer media: type: array items: type: object properties: id: type: string title: anyOf: - type: string - type: 'null' type: anyOf: - type: string enum: - DPA - VIDEO - CAROUSEL - IMAGE - DCO - type: 'null' mediaType: anyOf: - type: string enum: - VIDEO - IMAGE - type: 'null' mediaUrl: anyOf: - type: string - type: 'null' thumbnailUrl: anyOf: - type: string - type: 'null' platforms: type: array items: type: string hook: anyOf: - type: string - type: 'null' startAt: anyOf: - type: string - type: 'null' endAt: anyOf: - type: string - type: 'null' daysRun: anyOf: - type: number - type: 'null' categories: type: array items: type: string carouselCount: anyOf: - type: number - type: 'null' viewCount: anyOf: - type: number - type: 'null' likeCount: anyOf: - type: number - type: 'null' commentCount: anyOf: - type: number - type: 'null' impressionPercentile: anyOf: - type: number - type: 'null' impressionsText: anyOf: - type: string - type: 'null' required: - id - title - type - mediaType - mediaUrl - thumbnailUrl - platforms - hook - startAt - endAt - daysRun - categories - carouselCount - viewCount - likeCount - commentCount - impressionPercentile - impressionsText required: - count - media '400': $ref: '#/components/responses/InvalidRequest' '401': $ref: '#/components/responses/InvalidApiKey' '402': $ref: '#/components/responses/OutOfCredits' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/BrandNotFound' '405': $ref: '#/components/responses/MethodNotAllowed' '413': $ref: '#/components/responses/PayloadTooLarge' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' components: responses: InvalidRequest: description: >- The request body or query string failed validation. `details` lists the offending fields. content: application/json: schema: $ref: '#/components/schemas/Error' InvalidApiKey: description: The API key is missing, malformed, unknown, or revoked. content: application/json: schema: $ref: '#/components/schemas/Error' OutOfCredits: description: The team's monthly credits are exhausted. content: application/json: schema: $ref: '#/components/schemas/Error' Forbidden: description: The team's subscription is inactive, or your membership of it has ended. content: application/json: schema: $ref: '#/components/schemas/Error' BrandNotFound: description: No brand matches that id. content: application/json: schema: $ref: '#/components/schemas/Error' MethodNotAllowed: description: >- The HTTP method is not supported on this path. The Allow header lists what is. HEAD is refused on metered GET endpoints because it would be billed without returning data. content: application/json: schema: $ref: '#/components/schemas/Error' PayloadTooLarge: description: The request body exceeds the 100 KB limit. content: application/json: schema: $ref: '#/components/schemas/Error' RateLimited: description: >- Too many requests. Carries a Retry-After header. Limits are 60/minute per IP, 120/minute per key, plus the per-endpoint limit stated on the operation. content: application/json: schema: $ref: '#/components/schemas/Error' InternalError: description: Something went wrong on our side. content: application/json: schema: $ref: '#/components/schemas/Error' schemas: Error: type: object required: - error properties: error: type: object required: - code - message properties: code: type: string enum: - invalid_request - invalid_api_key - payload_too_large - out_of_credits - membership_ended - subscription_inactive - brand_not_found - not_found - method_not_allowed - rate_limited - internal_error message: type: string details: type: array items: type: object required: - path - message properties: path: type: string message: type: string securitySchemes: bearerAuth: type: http scheme: bearer description: An API key from Settings → API, prefixed sg_live_. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.