--- title: Get an AI Search instance. --- [Skip to content](#_top) [API Reference](https://developers.cloudflare.com/api) [AI Search](https://developers.cloudflare.com/api/resources/ai_search) [Instances](https://developers.cloudflare.com/api/resources/ai_search/subresources/instances) Copy Markdown Open in **Claude**Open in **ChatGPT**Open in **Cursor** --- **Copy Markdown****View as Markdown** # Get an AI Search instance. Deprecated GET/accounts/{account\_id}/ai-search/instances/{id} Retrieve the configuration and status of an AI Search instance. Deprecated: use /accounts/{account\_id}/ai-search/namespaces/{name}/instances (and descendant paths) instead. ##### Security

API Token

The preferred authorization scheme for interacting with the Cloudflare API. Create a token. **Example:**Authorization: Bearer Sn3lZJTBX6kkg7OdcBUAxOO963GEIyGQqnFTOFYY

API Email + API Key

The previous authorization scheme for interacting with the Cloudflare API, used in conjunction with a Global API key. **Example:**X-Auth-Email: user@example.com The previous authorization scheme for interacting with the Cloudflare API. When possible, use API tokens instead of Global API keys. **Example:**X-Auth-Key: 144c9defac04969c7bfad8efaa8ea194

##### P ath ParametersExpand Collapse account\_id: string [Link to this property](<#(resource)%20ai_search.instances%20%3E%20(method)%20read%20%3E%20(params)%20default%20%3E%20(param)%20account_id%20%3E%20(schema)>) id: string [Link to this property](<#(resource)%20ai_search.instances%20%3E%20(method)%20read%20%3E%20(params)%20default%20%3E%20(param)%20id%20%3E%20(schema)>) ##### ReturnsExpand Collapse

result: object {id, created\_at, modified\_at, 36 more }

id: string AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores. maxLength64 minLength1 Link to this property created\_at: string formatdate-time Link to this property modified\_at: string formatdate-time Link to this property ai\_gateway\_id: optional string Link to this property ai\_search\_model: optional string A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model. Link to this property cache: optional boolean Link to this property

cache\_threshold: optional "super\_strict\_match"or "close\_enough"or "flexible\_friend"or "anything\_goes"

One of the following: "super\_strict\_match" Link to this property "close\_enough" Link to this property "flexible\_friend" Link to this property "anything\_goes" Link to this property

Link to this property

cache\_ttl: optional 600or 1800or 3600or 7 more Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600 (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200 (72h), 518400 (6d).

One of the following: 600 Link to this property 1800 Link to this property 3600 Link to this property 7200 Link to this property 21600 Link to this property 43200 Link to this property 86400 Link to this property 172800 Link to this property 259200 Link to this property 518400 Link to this property

Link to this property chunk\_overlap: optional number maximum30 minimum0 Link to this property chunk\_size: optional number minimum64 Link to this property created\_by: optional string Link to this property

custom\_metadata: optional array of object {data\_type, field\_name }

data\_type: "text"or "number"or "boolean"or "datetime"

One of the following: "text" Link to this property "number" Link to this property "boolean" Link to this property "datetime" Link to this property

Link to this property field\_name: string maxLength64 minLength1 Link to this property

Link to this property embedding\_model: optional string Link to this property enable: optional boolean Link to this property engine\_version: optional number Link to this property

fusion\_method: optional "max"or "rrf"

One of the following: "max" Link to this property "rrf" Link to this property

Link to this property Deprecatedhybrid\_search\_enabled: optional boolean Deprecated — use index\_method instead. Defaults to true for new instances; set false to create a vector-only instance. Link to this property

index\_method: optional object {keyword, vector } Controls which storage backends are used during indexing. Defaults to vector and keyword indexing for new instances.

keyword: boolean Enable keyword (BM25) storage backend. Link to this property vector: boolean Enable vector (embedding) storage backend. Link to this property

Link to this property

indexing\_options: optional object {keyword\_tokenizer, use\_ocr }

keyword\_tokenizer: optional "porter"or "trigram" Tokenizer used for keyword search indexing. porter provides word-level tokenization with Porter stemming (good for natural language queries). trigram enables character-level substring matching (good for partial matches, code, identifiers). Changing this triggers a full re-index. Defaults to porter.

One of the following: "porter" Link to this property "trigram" Link to this property

Link to this property use\_ocr: optional boolean Enables OCR ingestion for PDFs and images. Changing this triggers a full re-index. Defaults to false. Link to this property

Link to this property last\_activity: optional string formatdate-time Link to this property max\_num\_results: optional number maximum50 minimum1 Link to this property

metadata: optional object {created\_from\_aisearch\_wizard, worker\_domain }

created\_from\_aisearch\_wizard: optional boolean Link to this property worker\_domain: optional string Link to this property

Link to this property modified\_by: optional string Link to this property namespace: optional string Link to this property paused: optional boolean Link to this property public\_endpoint\_id: optional string Link to this property

public\_endpoint\_params: optional object {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more }

authorized\_hosts: optional array of string Link to this property

chat\_completions\_endpoint: optional object {disabled }

disabled: optional boolean Disable chat completions endpoint for this public endpoint Link to this property

Link to this property custom\_domains: optional array of string Custom domain hostnames that alias this public endpoint. GET and create responses return the current set; on update (PUT) this field is only echoed back when supplied in the request body, otherwise it is null (omit it to leave domains unchanged). Link to this property default\_domain\_enabled: optional boolean When false, the instance is reachable only via a registered custom domain and the default <public\_endpoint\_id>.search.ai.cloudflare.com host returns 404. Requires at least one custom domain. Defaults to true. public\_endpoint\_params is replaced wholesale on update, so resend default\_domain\_enabled on every update to keep the default host off — omitting it resets to true. Link to this property enabled: optional boolean Link to this property

mcp: optional object {description, disabled }

description: optional string Link to this property disabled: optional boolean Disable MCP endpoint for this public endpoint Link to this property

Link to this property

rate\_limit: optional object {period\_ms, requests, technique }

period\_ms: optional number maximum3600000 minimum60000 Link to this property requests: optional number minimum1 Link to this property

technique: optional "fixed"or "sliding"

One of the following: "fixed" Link to this property "sliding" Link to this property

Link to this property

search\_endpoint: optional object {disabled }

disabled: optional boolean Disable search endpoint for this public endpoint Link to this property

Link to this property

Link to this property reranking: optional boolean Link to this property reranking\_model: optional string Link to this property

retrieval\_options: optional object {boost\_by, keyword\_match\_mode }

boost\_by: optional array of object {field, direction } Metadata fields to boost search results by. Each entry specifies a metadata field and an optional direction. Direction defaults to ‘asc’ for numeric/datetime fields and ‘exists’ for text/boolean fields. Fields must match ‘timestamp’ or a defined custom\_metadata field.

field: string Metadata field name to boost by. Use ‘timestamp’ for document freshness, or any custom\_metadata field. Numeric and datetime fields support all four directions (asc, desc, exists, not\_exists); text/boolean fields only support exists/not\_exists. maxLength64 minLength1 Link to this property

direction: optional "asc"or "desc"or "exists"or "not\_exists" Boost direction. ‘desc’ = higher values rank higher (e.g. newer timestamps). ‘asc’ = lower values rank higher. ‘exists’ = boost chunks that have the field. ‘not\_exists’ = boost chunks that lack the field. Optional — defaults to ‘asc’ for numeric/datetime fields, ‘exists’ for text/boolean fields.

One of the following: "asc" Link to this property "desc" Link to this property "exists" Link to this property "not\_exists" Link to this property

Link to this property

keyword\_match\_mode: optional "and"or "or" Controls which documents are candidates for BM25 scoring. ‘and’ restricts candidates to documents containing all query terms; ‘or’ includes any document containing at least one term, ranked by BM25 relevance. When omitted on an update, the existing stored value is preserved; when never set, search falls back to ‘and’.

One of the following: "and" Link to this property "or" Link to this property

Link to this property

Link to this property rewrite\_model: optional string A Workers AI model ID or an AI Gateway model ID compatible with the OpenAI Chat Completions API. An empty string uses the configured or default model. Link to this property rewrite\_query: optional boolean Link to this property score\_threshold: optional number maximum1 minimum0 Link to this property source: optional string Link to this property

source\_params: optional object {exclude\_items, include\_items, prefix, 2 more }

exclude\_items: optional array of string List of path patterns to exclude. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /admin/\*\* matches /admin/users and /admin/settings/advanced). Most accounts are limited to 10 rules; contact support to raise it. Link to this property include\_items: optional array of string List of path patterns to include. Uses micromatch glob syntax: \* matches within a path segment, \*\* matches across path segments (e.g., /blog/\*\* matches /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact support to raise it. Link to this property prefix: optional string Link to this property r2\_jurisdiction: optional string Link to this property

web\_crawler: optional object {discover\_options, parse\_options, parse\_type }

discover\_options: optional object {depth, include\_external\_links, include\_subdomains, 3 more } Options for parse\_type ‘discover’, where Browser Run discovers URLs by link following and sitemaps. Ignored for ‘sitemap’.

depth: optional number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links: optional boolean Follow links that point outside the source domain. Must stay false — discover crawls are restricted to the zone you own. Link to this property include\_subdomains: optional boolean Follow links to subdomains of the source host. Link to this property limit: optional number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age: optional number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property

source: optional "all"or "sitemaps"or "links" Where the crawler looks for URLs: ‘sitemaps’ reads sitemap XML only, ‘links’ follows page links only, ‘all’ does both.

One of the following: "all" Link to this property "sitemaps" Link to this property "links" Link to this property

Link to this property

parse\_options: optional object {content\_selector, include\_headers, include\_images, 2 more }

content\_selector: optional array of object {path, selector } List of path-to-selector mappings for extracting specific content from crawled pages. Each entry pairs a URL glob pattern with a CSS selector. The first matching path wins. Only the matched HTML fragment is stored and indexed. Omit the field to disable content selection — empty arrays are rejected.

path: string Glob pattern to match against the page URL path. Uses standard glob syntax: \* matches within a segment, \*\* crosses directories. maxLength200 minLength1 Link to this property selector: string CSS selector to extract content from pages matching the path pattern. Must not contain disallowed characters (;, \`, $, {, }, ). Must target a single element; if multiple elements match, the selector is ignored and the full page is used. maxLength200 minLength1 Link to this property

Link to this property include\_headers: optional map\[string] Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230 token characters (no spaces, colons, or control characters); values must be HTAB + printable ASCII (no CR/LF). Link to this property include\_images: optional boolean Link to this property specific\_sitemaps: optional array of string List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering: optional boolean Link to this property

Link to this property

parse\_type: optional "sitemap"or "discover" How URLs are discovered. ‘sitemap’ reads XML sitemaps; ‘discover’ follows links recursively and requires the source to be a Verified zone on this account.

One of the following: "sitemap" Link to this property "discover" Link to this property

Link to this property

Link to this property status: optional string Link to this property

sync\_interval: optional 900or 1800or 3600or 5 more Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800 (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).

One of the following: 900 Link to this property 1800 Link to this property 3600 Link to this property 7200 Link to this property 14400 Link to this property 21600 Link to this property 43200 Link to this property 86400 Link to this property

Link to this property token\_id: optional string formatuuid Link to this property

type: optional "r2"or "web-crawler" Source type. When omitted or null with a non-blank source, HTTP(S) URLs infer web-crawler and existing R2 bucket names infer r2. A missing or blank source without a type uses managed upload-only storage.

One of the following: "r2" Link to this property "web-crawler" Link to this property

Link to this property

[Link to this property](<#(resource)%20ai_search.instances%20%3E%20(method)%20read%20%3E%20(network%20schema)%20%3E%20(property)%20result>) success: boolean [Link to this property](<#(resource)%20ai_search.instances%20%3E%20(method)%20read%20%3E%20(network%20schema)%20%3E%20(property)%20success>) ### Get an AI Search instance. HTTP HTTPTypeScriptPythonGoTerraform ``` curl https://api.cloudflare.com/client/v4/accounts/$ACCOUNT_ID/ai-search/instances/$ID \ -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" ``` 200 example ``` { "result": { "id": "my-ai-search", "created_at": "2019-12-27T18:11:19.117Z", "modified_at": "2019-12-27T18:11:19.117Z", "ai_gateway_id": "ai_gateway_id", "ai_search_model": "ai_search_model", "cache": true, "cache_threshold": "super_strict_match", "cache_ttl": 600, "chunk_overlap": 0, "chunk_size": 64, "created_by": "created_by", "custom_metadata": [ { "data_type": "text", "field_name": "x" } ], "embedding_model": "embedding_model", "enable": true, "engine_version": 0, "fusion_method": "max", "hybrid_search_enabled": true, "index_method": { "keyword": true, "vector": true }, "indexing_options": { "keyword_tokenizer": "porter", "use_ocr": true }, "last_activity": "2019-12-27T18:11:19.117Z", "max_num_results": 1, "metadata": { "created_from_aisearch_wizard": true, "worker_domain": "worker_domain" }, "modified_by": "modified_by", "namespace": "namespace", "paused": true, "public_endpoint_id": "public_endpoint_id", "public_endpoint_params": { "authorized_hosts": [ "string" ], "chat_completions_endpoint": { "disabled": true }, "custom_domains": [ "search.example.com" ], "default_domain_enabled": true, "enabled": true, "mcp": { "description": "description", "disabled": true }, "rate_limit": { "period_ms": 60000, "requests": 1, "technique": "fixed" }, "search_endpoint": { "disabled": true } }, "reranking": true, "reranking_model": "reranking_model", "retrieval_options": { "boost_by": [ { "field": "timestamp", "direction": "desc" } ], "keyword_match_mode": "and" }, "rewrite_model": "rewrite_model", "rewrite_query": true, "score_threshold": 0, "source": "source", "source_params": { "exclude_items": [ "/admin/**", "/private/**", "**\\temp\\**" ], "include_items": [ "/blog/**", "/docs/**/*.html", "**\\blog\\**.html" ], "prefix": "prefix", "r2_jurisdiction": "r2_jurisdiction", "web_crawler": { "discover_options": { "depth": 5, "include_external_links": false, "include_subdomains": false, "limit": 10000, "max_age": 86400, "source": "all" }, "parse_options": { "content_selector": [ { "path": "**/blog/**", "selector": "article div.post-body" }, { "path": "**/docs/**", "selector": "main" } ], "include_headers": { "cache-control": "no-cache, no-store" }, "include_images": true, "specific_sitemaps": [ "https://example.com/sitemap.xml", "https://example.com/blog-sitemap.xml" ], "use_browser_rendering": true }, "parse_type": "sitemap" } }, "status": "status", "sync_interval": 900, "token_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "type": "r2" }, "success": true } ``` ##### Returns Examples 200 example ``` { "result": { "id": "my-ai-search", "created_at": "2019-12-27T18:11:19.117Z", "modified_at": "2019-12-27T18:11:19.117Z", "ai_gateway_id": "ai_gateway_id", "ai_search_model": "ai_search_model", "cache": true, "cache_threshold": "super_strict_match", "cache_ttl": 600, "chunk_overlap": 0, "chunk_size": 64, "created_by": "created_by", "custom_metadata": [ { "data_type": "text", "field_name": "x" } ], "embedding_model": "embedding_model", "enable": true, "engine_version": 0, "fusion_method": "max", "hybrid_search_enabled": true, "index_method": { "keyword": true, "vector": true }, "indexing_options": { "keyword_tokenizer": "porter", "use_ocr": true }, "last_activity": "2019-12-27T18:11:19.117Z", "max_num_results": 1, "metadata": { "created_from_aisearch_wizard": true, "worker_domain": "worker_domain" }, "modified_by": "modified_by", "namespace": "namespace", "paused": true, "public_endpoint_id": "public_endpoint_id", "public_endpoint_params": { "authorized_hosts": [ "string" ], "chat_completions_endpoint": { "disabled": true }, "custom_domains": [ "search.example.com" ], "default_domain_enabled": true, "enabled": true, "mcp": { "description": "description", "disabled": true }, "rate_limit": { "period_ms": 60000, "requests": 1, "technique": "fixed" }, "search_endpoint": { "disabled": true } }, "reranking": true, "reranking_model": "reranking_model", "retrieval_options": { "boost_by": [ { "field": "timestamp", "direction": "desc" } ], "keyword_match_mode": "and" }, "rewrite_model": "rewrite_model", "rewrite_query": true, "score_threshold": 0, "source": "source", "source_params": { "exclude_items": [ "/admin/**", "/private/**", "**\\temp\\**" ], "include_items": [ "/blog/**", "/docs/**/*.html", "**\\blog\\**.html" ], "prefix": "prefix", "r2_jurisdiction": "r2_jurisdiction", "web_crawler": { "discover_options": { "depth": 5, "include_external_links": false, "include_subdomains": false, "limit": 10000, "max_age": 86400, "source": "all" }, "parse_options": { "content_selector": [ { "path": "**/blog/**", "selector": "article div.post-body" }, { "path": "**/docs/**", "selector": "main" } ], "include_headers": { "cache-control": "no-cache, no-store" }, "include_images": true, "specific_sitemaps": [ "https://example.com/sitemap.xml", "https://example.com/blog-sitemap.xml" ], "use_browser_rendering": true }, "parse_type": "sitemap" } }, "status": "status", "sync_interval": 900, "token_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "type": "r2" }, "success": true } ```