> ## Documentation Index > Fetch the complete documentation index at: https://docs.electronhub.ai/llms.txt > Use this file to discover all available pages before exploring further. # Export Policy > A portable copy of the policy for backup or sharing. Import it with the import endpoint. ## OpenAPI ````yaml GET /router/policies/{policy_id}/export openapi: 3.0.1 info: title: Electron Hub API description: >- Unified API platform integrating 200+ AI models for chat, image generation, speech-to-text, embeddings, and more. version: 1.0.0 contact: name: Electron Hub Support email: support@electronhub.ai url: https://discord.com/invite/electronhub license: name: MIT servers: - url: https://api.electronhub.ai/v1 description: Production API v1 security: - bearerAuth: [] paths: /router/policies/{policy_id}/export: get: tags: - Router summary: Export policy description: >- A portable copy of the policy for backup or sharing. Import it with the import endpoint. operationId: exportRouterPolicy parameters: - name: policy_id in: path required: true schema: type: string pattern: ^[a-z0-9-]{1,40}$ example: work responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/RouterPolicy' example: policyId: work name: Work schemaVersion: 4 mode: auto auto: costTier: high qualityFloor: 0 preferFast: false preferVendor: null preferStrength: 0 maxTtft: 0 perCategory: {} custom: rules: [] default: - action: useAuto models: allowed: [] excluded: - '*:free' strictAllowed: false guardrails: maxCostPerReq: null blockOverCost: false budgetUsd: 5 budgetWindow: daily budgetScope: routed blockOverBudget: false pii: enabled: false action: block model: null entities: {} labels: {} custom: [] scanAll: false cache: enabled: false ttlMin: 1440 maxEntries: 100 semantic: false semanticThreshold: 0.9 kind: electron-hub.router-policy exportedAt: '2026-11-08T07:34:14.933183Z' '403': description: Proxy keys cannot manage Router settings content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Only master keys can manage Router settings. type: error param: null code: 403 '404': description: Policy not found content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Router policy “missing” was not found. type: router_policy_not_found param: null code: 404 components: schemas: RouterPolicy: type: object description: >- Missing fields take defaults. See https://docs.electronhub.ai/routing/auto-router#policies properties: policyId: type: string pattern: ^[a-z0-9-]{1,40}$ name: type: string schemaVersion: type: integer example: 4 mode: type: string enum: - auto - custom description: '`custom` evaluates `custom.rules` first.' auto: type: object properties: costTier: type: string enum: - low - medium - high - xhigh - max default: medium qualityFloor: type: number minimum: 0 maximum: 100 description: Minimum benchmark score (0 = off). preferFast: type: boolean description: Prefer models with the fastest end-to-end response. preferVendor: type: string nullable: true description: Vendor to favour, e.g. `Anthropic`. preferStrength: type: number minimum: 0 maximum: 0.2 description: How strongly to favour `preferVendor`. maxTtft: type: number minimum: 0 description: Maximum seconds to the first answer token (0 = off). perCategory: type: object additionalProperties: type: string description: >- Fixed model per category, e.g. `{"coding": "claude-sonnet-5-5"}`. custom: type: object properties: rules: type: array items: type: object description: >- Ordered rules: `when` conditions on request signals, `then` actions. default: type: array items: type: object description: 'Actions when no rule matches. Default `[{"action": "useAuto"}]`.' models: type: object properties: allowed: type: array items: type: string description: Model patterns, e.g. `anthropic/*`. excluded: type: array items: type: string strictAllowed: type: boolean description: Fail with 404 when `allowed` matches nothing. guardrails: type: object properties: maxCostPerReq: type: number nullable: true description: Estimated cost cap per request, in USD. blockOverCost: type: boolean description: Block instead of downgrading when over `maxCostPerReq`. budgetUsd: type: number nullable: true description: Spend budget per window, in USD. budgetWindow: type: string enum: - daily - weekly - monthly description: Windows start at 00:00 UTC. budgetScope: type: string enum: - routed - all description: Count Auto requests only, or all spend. blockOverBudget: type: boolean description: >- Block instead of using the cheapest model when the budget is spent. pii: type: object description: Privacy guard. properties: enabled: type: boolean action: type: string enum: - block - redact - route model: type: string nullable: true description: 'Model for `action: route`.' entities: type: object additionalProperties: type: boolean description: Entity types to detect; empty means all except `name`. scanAll: type: boolean description: Scan every message, not only the latest. cache: type: object description: Response cache for repeated requests. properties: enabled: type: boolean ttlMin: type: integer minimum: 1 maximum: 43200 maxEntries: type: integer minimum: 1 maximum: 5000 semantic: type: boolean description: Also match similar, not only identical, requests. semanticThreshold: type: number minimum: 0.8 maximum: 0.99 Error: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string type: type: string code: type: string securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: Enter your API key (starts with 'ek-') ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.