> ## Documentation Index > Fetch the complete documentation index at: https://developers.meshapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # Memory Usage > Per-memID request counts, injected tokens, and last-used, plus embed cost. MUST stay declared ABOVE `GET /{slug_or_id}` — FastAPI matches in declaration order, so below it "usage" is read as a slug and this route is unreachable (404, from a memory nobody owns). Scoped to the CALLER'S OWN keys, not the whole org, and that is the honest scope rather than a shortcut: injection is owner-scoped in the gateway, so a colleague's memID cannot be attached by your keys at all. It also sidesteps a real ambiguity — `memory_slugs` records slugs, and slugs are unique per (owner, slug) rather than per org, so an org-wide aggregate would silently merge two members' identically-named memories into one row. Every token figure is OUR tokenizer's estimate of what the injected block cost, not a provider-reported number: no upstream reports the split between the memory block and the rest of the prompt. A request attaching several memIDs logs ONE block size, which is split equally across them here — see the subquery. Hence `injected_tokens_est`, and hence no derived dollar figure beside it — see MemoryUsageRow. ## OpenAPI ````yaml /api/openapi.json get /v1/memories/usage openapi: 3.1.0 info: title: MeshAPI description: One key, all AI models. version: 0.1.0 servers: - url: https://api.meshapi.ai security: - BearerAuth: [] paths: /v1/memories/usage: get: tags: - Memory summary: Memory Usage description: >- Per-memID request counts, injected tokens, and last-used, plus embed cost. MUST stay declared ABOVE `GET /{slug_or_id}` — FastAPI matches in declaration order, so below it "usage" is read as a slug and this route is unreachable (404, from a memory nobody owns). Scoped to the CALLER'S OWN keys, not the whole org, and that is the honest scope rather than a shortcut: injection is owner-scoped in the gateway, so a colleague's memID cannot be attached by your keys at all. It also sidesteps a real ambiguity — `memory_slugs` records slugs, and slugs are unique per (owner, slug) rather than per org, so an org-wide aggregate would silently merge two members' identically-named memories into one row. Every token figure is OUR tokenizer's estimate of what the injected block cost, not a provider-reported number: no upstream reports the split between the memory block and the rest of the prompt. A request attaching several memIDs logs ONE block size, which is split equally across them here — see the subquery. Hence `injected_tokens_est`, and hence no derived dollar figure beside it — see MemoryUsageRow. operationId: memory_usage parameters: - name: window_days in: query required: false schema: type: integer maximum: 90 minimum: 1 default: 30 title: Window Days - in: header name: X-Mesh-Version required: false schema: type: string enum: - 2026-08 default: 2026-08 example: 2026-08 description: >- Dated version of the API contract to pin this request to. Omit it and the request is served under `2026-08` — the oldest supported version, so an existing integration is never moved by a release. A malformed or unsupported value is rejected with `400 invalid_api_version` rather than falling back silently. The version actually served is echoed as `X-Mesh-Version` on every response, including errors. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MemoryUsageResponse' '401': description: Missing or invalid credentials '422': description: window_days out of range security: - BearerAuth: [] components: schemas: MemoryUsageResponse: properties: window_days: type: integer title: Window Days tracked_since: anyOf: - type: string - type: 'null' title: Tracked Since memories: items: $ref: '#/components/schemas/MemoryUsageRow' type: array title: Memories default: [] embed_requests: type: integer title: Embed Requests default: 0 embed_cost_usd: type: string title: Embed Cost Usd default: '0' type: object required: - window_days title: MemoryUsageResponse MemoryUsageRow: properties: slug: type: string title: Slug requests: type: integer title: Requests default: 0 injected_tokens_est: type: integer title: Injected Tokens Est default: 0 last_used_at: anyOf: - type: string - type: 'null' title: Last Used At per_key: items: $ref: '#/components/schemas/MemoryUsageKeyRow' type: array title: Per Key default: [] type: object required: - slug title: MemoryUsageRow description: >- Usage for one memID, as used by the caller's own API keys. ``injected_tokens_est`` is doubly an estimate. It is OUR tokenizer's count of the block we prepended — no provider reports the split between that block and the rest of the prompt — AND, when a request attached several memIDs, this memory's equal share of that one block rather than its measured contribution. Which is why there is deliberately no dollar figure beside it: calling an estimate a charge on a billing-adjacent surface is how numbers get quoted back at you in a support ticket. MemoryUsageKeyRow: properties: key_id: type: string title: Key Id requests: type: integer title: Requests injected_tokens_est: type: integer title: Injected Tokens Est type: object required: - key_id - requests - injected_tokens_est title: MemoryUsageKeyRow securitySchemes: BearerAuth: type: http scheme: bearer description: >- Enter your MeshAPI key (`rsk_...`) — sent as `Authorization: Bearer `. ````