--- title: "Search the web" method: GET path: "/api/v1/search" --- # Search the web `GET /api/v1/search` ## Request - Base URL: `https://api.andiai.com` - URL: `https://api.andiai.com/api/v1/search` - Auth: API key in header `x-api-key` Performs a web search and returns structured results. Search effort is set automatically per query by default (`searchMode=auto`), with fixed modes (low-cost, fast, balanced, deep, exhaustive) available for manual control. Supports domain and date filtering, query operators, and multiple output formats. ## Query parameters - `q` string, required - `limit` integer - `offset` integer - `searchMode` 'auto' | 'low-cost' | 'fast' | 'balanced' | 'deep' | 'exhaustive' - `effort` 'low' | 'medium' | 'high' | 'max' - `reranker` 'auto' | 'small' | 'medium' | 'large' | 'xl' - `intent` string - `format` 'json' | 'context' - `metadata` 'basic' | 'full' - `extracts` boolean - `content` 'true' | 'focused' | 'false' - `enrichContent` boolean - `maxContentLength` integer - `timeout` integer - `safe` 'off' | 'moderate' | 'strict' - `country` string - `sourceCountry` string - `language` string - `languageMode` 'prefer' | 'strict' - `units` 'metric' | 'imperial' - `noCache` boolean - `dateRange` 'day' | 'week' | 'month' | 'year' | '24h' | '7d' | '30d' | '90d' | '1y' - `dateFrom` string, date - `dateTo` string, date - `includeDomains` string - `excludeDomains` string - `includeTerms` string - `excludeTerms` string - `parseOperators` boolean - `linkFormat` 'link' | 'url' - `imageFormat` 'short' | 'long' - `filetype` string - `intitle` string - `inurl` string - `intext` string ## Response `200` Search results. JSON by default; LLM-ready markdown with YAML frontmatter when `format=context`. - SearchResponse - `results_type` string, required: The type of results returned (e.g., `Search`, `News`, `Weather`, `Calculator`). Determines which optional response sections are present. - `answer` string, required: Instant answer for the query when one is found — for example a definition, a weather line or a calculation — otherwise an empty string. On news feeds, a short summary of the headlines when available. - `type` string, required: Same as `results_type`. Indicates the category of results. - `title` string, required: Your query text (for a news feed, the feed's description). - `results` SearchResult[], required: Array of search results. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `metrics` Metrics, required: Search performance metrics. Always included in the response. - `query` string: The query as processed. - `intent` string: The detected or forced search intent. - `timestamp` string: Timestamp of the search request. - `duration` number: Total request duration in milliseconds. - `queries_executed` integer: Number of search queries executed. - `api_requests_count` integer: Number of queries in your request (the same as `queries_executed`). - `results_returned` integer: Number of results returned in this response. - `total_results_found` integer: Rough estimate of matching pages, as reported by sources (0 for news feeds). - `queries_provided` integer: Number of queries you sent. Only present when more than 5 were sent. - `queries_truncated` integer: How many queries were dropped because only the first 5 run. Only present when more than 5 were sent. - `cached` boolean: Whether the response was served from cache. Only present on cache hits. - `cache_age_seconds` integer: Age of the cached response in seconds. Only present on cache hits. - `cost_dollars` number: Amount charged to your account for this request in USD, after any discounts. Pricing is outcome-based — each request is charged for the work performed and the content delivered, whether the effort was set automatically (`auto`) or pinned with a fixed mode. - `effort` 'low' | 'medium' | 'high' | 'max': Resolved effort tier for this request — the tier `auto` mode selected, or the one pinned via `searchMode`/`effort`. - `response_time_ms` integer: Total server response time in milliseconds. - `correctedQuery` string: Spell-corrected query. Present when a misspelling in the original query is detected and corrected — any mode can return it; deep and exhaustive modes run the strongest spell correction. - `related_searches` string[]: Related search suggestions. Present on some queries. - `topics` string[]: Related topics. Present on some queries. - `related_topics` string[]: Related topic names for entity answers. - `infobox` object: Facts panel for an entity answer. - `heading` string - `source` string - `items` object[] - `label` string - `value` string - `disambiguation` object: Possible meanings when the query is ambiguous. - `query` string - `message` string - `options` object[] - `title` string - `text` string - `url` string, uri - `aiSummary` object: A pre-written news summary. News feeds return it, and so does search when the query asks for a whole feed (for example "latest technology news" or "hacker news"), but not for a topic inside a feed ("nfl news"). On news feeds the same text is in `answer`; on search, `answer` can hold something else, such as a description of the site. - `text` string: The summary, as markdown. - `generatedAt` string, date-time: When the summary was written. - `model` string: A short label for the summary's source. - `mode` 'pregen': `pregen` means the summary was written ahead of your request. - `locale` object: The language and country Andi searched for. Present on every search response (not on news feeds). With `format=context`, the same values appear in the frontmatter as `language`, `language_confidence`, `language_source`, `country` and `local_scope`. - `language` string, required: ISO 639-1 code of the query language, or `und` when unknown. - `languageConfidence` number, required: Confidence in `language`, from 0 to 1. - `languageSource` 'param' | 'script' | 'jev' | 'none', required: Where `language` came from: `param` (you stated it), `script` (the query's writing system named it), `jev` (detected from the words), or `none`. - `country` string: ISO 3166-1 country code the search was scoped to. Left out when unknown. - `localScope` 'global' | 'country' | 'city': How much the answer depends on the searcher's place. Left out when not judged. - `safeSearch` object: Echo of the safe-search state. Present on cache misses. Use it to confirm your `safe` parameter was honored. - `requested` 'off' | 'moderate' | 'strict' - `applied` 'off' | 'moderate' | 'strict' - `videos` SearchResult[]: Video results, when the search found any. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `images` ImageResult[]: Image results, when the search found any. - `title` string, required: Image title or alt text. - `link` string, uri, required: URL of the page containing the image. - `image` string, uri, required: Direct URL of the full-size image. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'image', required: Always `image`. - `thumbnail` string, uri: Thumbnail URL. - `width` string: Image width in pixels (as a string). - `height` string: Image height in pixels (as a string). - `news` SearchResult[]: News stories, when the search found any. Front pages, section pages, topic pages and listing pages are in `categories`, not here. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `citations` SearchResult[]: Rows an answer cites, in the same shape as `results`. When a search names a whole curated news feed (for example "headlines" or "latest news from hacker news") and the response carries the feed's `aiSummary`, this lists the stories the summary cites in the summary's order, then the feed's other stories, up to `limit`. Left out when empty. Not on `/api/v1/news`. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `categories` SearchResult[]: News front pages, section pages, topic or tag pages, listing pages and site-search pages. `results` still holds them too. Left out when empty. Not on `/api/v1/news`. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `places` SearchResult[]: Place and business results, when the search found any. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `profiles` SearchResult[]: People and entity profiles, when the search found any. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `social` SearchResult[]: Social posts, when the search found any. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `academic` SearchResult[]: Scholarly papers, when the search found any. - `title` string, required: Page title. - `link` string, uri, required: Page URL. - `desc` string, required: Page description or summary. - `source` string, required: Site or publisher name (for example `Wikipedia`); a name derived from the domain when none is known. - `type` 'website' | 'blog' | 'news' | 'video' | 'image' | 'place' | 'profile' | 'social' | 'academic' | 'calculation' | 'weather' | 'computation' | 'instant answer': Result type. Only included when `metadata=full`. - `date` string: Publication date of the content, when available. - `dateModified` string: When the page was last updated, if known. - `image` string, uri: Preview image URL, when available. Only included when `metadata=full`. - `snippet` string: Query-relevant text excerpt from the page. Distinct from `desc`, which is the general page description. - `answer` string: Inline answer for instant answer results. - `extracts` string[]: Query-relevant passages from the page. Returned with `extracts=true`, and by default with `format=context`, `content=true` and `metadata=full`. - `contentType` string: Content type of the page. Only included when `metadata=full`. - `reader` object: Extracted page content and metadata. Included with `metadata=full`; with `content=true` it holds the full page text in `reader.markdown` (or `reader.content`) at any metadata level. - `contentSafety` object: Safety classification. Only included when `metadata=full`. - `rating` 'safe' | 'unsafe' | 'unknown': Content safety rating. - `safeSearchApplied` boolean: Whether safe-search filtering was applied to this result. - `bang` string: Bang shortcut for the result domain. Only included when `metadata=full`. - `queryIndices` integer[]: Multi-query only: which of your queries (0-based) found this result. - `language` string: The page's language as a lower-case primary tag, for example `fr`. Left out when unknown. - `site_country` string: ISO 3166-1 country code named by the site's country-code domain, for example `DE` for `.de`. Generic domains such as `.com` have none. - `seeAlso` object[]: News feeds only: other outlets covering the same story. - `title` string - `url` string, uri - `source` string - `weather` WeatherResult - `location` object, required: Location details. - `name` string: Location name. - `country` string: Country name or code. - `coordinates` object - `latitude` number - `longitude` number - `temperature` number, required: Current temperature. - `feelsLike` number: Feels-like temperature. - `units` 'metric' | 'imperial', required: Unit system: `metric` or `imperial`. - `description` string, required: Weather condition description. - `humidity` number: Humidity percentage. - `windSpeed` number: Wind speed. - `windDirection` number: Wind direction in degrees. - `pressure` number: Atmospheric pressure. - `icon` string: Weather icon identifier. - `cloudiness` number: Cloud cover percentage. - `visibility` number: Visibility distance. - `timestamp` integer: Time of the reading, Unix epoch milliseconds. - `calculation` CalculationResult - `expression` string, required: The mathematical expression. - `result` string, required: The calculated result. - `rawResult` unknown ## Other responses - `400`: Bad request — missing or invalid parameters - `401`: Unauthorized — missing or invalid API key - `402`: Insufficient credits — account balance depleted - `429`: Rate limit exceeded - `500`: Internal server error ## Changes - **2026-11-01** `fcda359bd8c6`: 1 breaking, 1 warning, 20 info - for the `query` request parameter `language`, default value `en` was removed - for the `query` request parameter `language`, the maxLength was set to `13` - added the new optional `query` request parameter `languageMode` - added the optional property `academic/items/language` to the response with the `200` status - …18 more - **2026-11-01** `44266783bfc1`: 2 info - added the optional property `categories` to the response with the `200` status - added the optional property `citations` to the response with the `200` status - **2026-10-29** `0f394ac8b1bb`: 2 breaking, 4 info - the `query` request parameter `content` was restricted to a list of enum values - for the `query` request parameter `content`, default value was changed from `false` to `false` - added the new enum value `false` to the `query` request parameter `content` - added the new enum value `focused` to the `query` request parameter `content` - …2 more - **2026-09-29** `7b56c4c1c3ea`: 1 breaking, 1 warning, 29 info - the `weather/timestamp` response's property type changed from `string` to `integer` for status `200` - removed the optional property `metrics/timing` from the response with the `200` status - added the optional property `academic/items/dateModified` to the response with the `200` status - added the optional property `academic/items/queryIndices` to the response with the `200` status - …27 more - …earlier changes not shown [Operation history](https://skmtc.dev/andiai/apis/andi-ai-search-api/changes/api/v1/search/get.md) --- [API](https://skmtc.dev/andiai/apis/andi-ai-search-api.md) - [All operations](https://skmtc.dev/andiai/apis/andi-ai-search-api/llms.txt) - [OpenAPI document](https://skmtc.dev/andiai/apis/andi-ai-search-api/revisions/fcda359bd8c6?raw)