> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > ## Agent Instructions (AIsa) > > - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative. > - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key. > - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste. > - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`. > - Paid calls need approval first. Docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP discovery are free to read. Before any paid, dynamically priced, or high-cost call, state the exact scope, rate, and maximum USD exposure, then wait for a separate user message approving that scope and cap. A request to collect data is not approval; do not send unapproved probes. Full rule: https://aisa.one/docs/llms.txt # Perform Smart Search ## Cost and request rules Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar. * **Default request reference estimate (USD):** 0.001 * **Cost contract:** fixed\_success * **Published reference multiplier:** 1.0 * **Settlement evidence source:** request\_snapshot ## OpenAPI ````yaml openapi/search.json GET /apis/v1/search/smart openapi: 3.1.0 info: description: '' title: Search version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-configured-paths: - /apis/v1/search/full - /apis/v1/search/smart x-aisa-document: facts_hash: ceb98c7e19d2df2aa61bdf4cea2cf7bdf468a7b6488ac7bf92e7eb777c9c38d7 generator_version: '3' protocol_version: '1' schema_version: '1' composer_version: '18' response_pending: [] document_hash: sha256:16b457fd3e40221bf6e072a68973d0f61dbe56415d44d7fd4cda542449fd0a3e x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: search x-aisa-catalogs: search: title: Search description: '' x-aisa-document: facts_hash: ceb98c7e19d2df2aa61bdf4cea2cf7bdf468a7b6488ac7bf92e7eb777c9c38d7 generator_version: '3' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /apis/v1/search/smart: get: tags: - search summary: Perform Smart Search operationId: any_search_apis_v1_search_smart parameters: - name: Pragma in: header required: false description: >- Input value: no-cache. When no-cache is provided, the response results will not be cached and each request is independent; if not provided, the response results for the same query term will be cached for 10 minutes schema: type: string - name: blockWebsites in: query required: false description: >- The value must be in host address format (e.g., baijiahao.baidu.com). Excludes results from the specified site(s). schema: type: string - name: contentTimeout in: query required: false description: >- Timeout for reading long abstracts. If reading exceeds this time, it will terminate and no long abstract will be returned for that result. Defaults to 0 (seconds), maximum 10s. schema: type: number default: 0 maximum: 10 - name: contentType in: query required: false description: >- The format of the long abstract (content) to return. Options:：- HTML- MARKDOWN- TEXT(default) schema: type: string enum: - HTML - MARKDOWN - TEXT default: TEXT - name: count in: query required: false description: >- The number of search results to return. Defaults to 10, maximum 50. Enumerated values: 10 / 20 / 30 / 40 / 50 The actual number returned may be less than requested. Use this parameter with the offset parameter for pagination. schema: type: integer default: 10 maximum: 50 enum: - 10 - 20 - 30 - 40 - 50 - name: enableContent in: query required: false description: >- ontrols whether to return long abstract content: -true: Return long abstracts -false: Do not return long abstracts Defaults to false schema: type: boolean default: false - name: freshness in: query required: false description: >- Filter search results by time range: - Day (past 24 hours) -Week (past 7 days) - Month (past 30 days) schema: type: string enum: - Day - Week - Month - name: mainText in: query required: false description: >- Controls whether to return key fragments of dynamic abstracts:true： Return key fragmentsfalse：Do not return key fragmentsDefault false schema: type: boolean default: false - name: offset in: query required: false description: >- The zero-based offset indicating how many results to skip before returning. Defaults to 0. Use with the count parameter for pagination. There is no upper limit for offset; setting a large value may result in no results being returned. schema: type: integer default: 0 minimum: 0 - name: q in: query required: true description: The user's search query term, which cannot be empty. schema: type: string minLength: 1 - name: sites in: query required: false description: >- The value must be in host address format (e.g., baijiahao.baidu.com). Returns results only from the specified site(s). schema: type: string responses: '200': description: >- Official typed response table; required fields and undeclared array item types are not inferred. content: application/json: schema: type: object properties: queryContext: type: object properties: originalQuery: type: string description: The user's original search query webPages: type: object properties: value: type: array description: Detailed result data returned items: type: object properties: name: type: string description: Webpage title url: type: string description: Webpage URL datePublished: type: string description: >- Page publication time (included in some sites) Example: 2025-07-14T01:15:00.0000000Z snippet: type: string description: Text snippet describing the webpage content mainText: type: string description: >- Dynamic abstract fragment extracted from the text, most relevant to the query. More intelligent than snippet siteName: type: string description: Website name (included in some webpages) contentCrawled: type: boolean description: >- Long abstract retrieval status: true for success (content is included in content), false for failure (content is empty) content: type: string description: >- Long abstract information of the webpage, retrieved from the main text. MARKDOWN and HTML formats include image links with anchor positions logo: type: string description: Website logo (included in some webpages) imageList: type: array description: >- List of image URLs in the webpage (included in some webpages, depending on whether the page contains images) score: type: number description: Content relevance score default: content: application/json: schema: {} description: >- Error response; upstream passthrough responses may use provider formats components: securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.