--- title: AI Search --- [Skip to content](#_top) [API Reference](https://developers.cloudflare.com/api/typescript) Copy Markdown Open in **Claude**Open in **ChatGPT**Open in **Cursor** --- **Copy Markdown****View as Markdown** # AI Search #### AI SearchNamespaces ##### [List namespaces](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/list) client.aiSearch.namespaces.list(NamespaceListParams {account\_id, page, per\_page, search } params, RequestOptionsoptions?): V4PagePaginationArray< [NamespaceListResponse]() {created\_at, name, description, 2 more } > GET/accounts/{account\_id}/ai-search/namespaces ##### [Create a namespace](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/create) client.aiSearch.namespaces.create(NamespaceCreateParams {account\_id, name, description, public\_endpoint\_params } params, RequestOptionsoptions?): [NamespaceCreateResponse]() {created\_at, name, description, 2 more } POST/accounts/{account\_id}/ai-search/namespaces ##### [Get a namespace](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/read) client.aiSearch.namespaces.read(stringname, NamespaceReadParams {account\_id } params, RequestOptionsoptions?): [NamespaceReadResponse]() {created\_at, name, description, 2 more } GET/accounts/{account\_id}/ai-search/namespaces/{name} ##### [Update a namespace](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/update) client.aiSearch.namespaces.update(stringname, NamespaceUpdateParams {account\_id, description, public\_endpoint\_params } params, RequestOptionsoptions?): [NamespaceUpdateResponse]() {created\_at, name, description, 2 more } PUT/accounts/{account\_id}/ai-search/namespaces/{name} ##### [Delete a namespace](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/delete) client.aiSearch.namespaces.delete(stringname, NamespaceDeleteParams {account\_id } params, RequestOptionsoptions?): [NamespaceDeleteResponse]() DELETE/accounts/{account\_id}/ai-search/namespaces/{name} ##### [Multi-Instance Search](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/search) client.aiSearch.namespaces.search(stringname, NamespaceSearchParams {account\_id, ai\_search\_options, messages, query } params, RequestOptionsoptions?): [NamespaceSearchResponse]() {chunks, query\_kind, errors, search\_query } POST/accounts/{account\_id}/ai-search/namespaces/{name}/search ##### [Multi-Instance Chat Completions](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/methods/chat_completions) client.aiSearch.namespaces.chatCompletions(stringname, NamespaceChatCompletionsParams {account\_id, ai\_search\_options, messages, 2 more } params, RequestOptionsoptions?): [NamespaceChatCompletionsResponse]() {choices, chunks, id, 3 more } POST/accounts/{account\_id}/ai-search/namespaces/{name}/chat/completions ##### ModelsExpand Collapse
NamespaceListResponse {created\_at, name, description, 2 more } created\_at: string| null formatdate-time Link to this property name: string Link to this property description?: string| null Optional description for the namespace. Max 256 characters. maxLength256 Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property instances\_allowed?: Array<string> Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit. Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_list_response%20%3E%20(schema)>)
NamespaceCreateResponse {created\_at, name, description, 2 more } created\_at: string| null formatdate-time Link to this property name: string Link to this property description?: string| null Optional description for the namespace. Max 256 characters. maxLength256 Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property instances\_allowed?: Array<string> Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit. Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_create_response%20%3E%20(schema)>)
NamespaceReadResponse {created\_at, name, description, 2 more } created\_at: string| null formatdate-time Link to this property name: string Link to this property description?: string| null Optional description for the namespace. Max 256 characters. maxLength256 Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property instances\_allowed?: Array<string> Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit. Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_read_response%20%3E%20(schema)>)
NamespaceUpdateResponse {created\_at, name, description, 2 more } created\_at: string| null formatdate-time Link to this property name: string Link to this property description?: string| null Optional description for the namespace. Max 256 characters. maxLength256 Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property instances\_allowed?: Array<string> Instance IDs exposed through the namespace public endpoint. Empty means nothing is searchable. Every ID must be an existing instance in this namespace, and the list cannot exceed the account’s multi-instance search limit. Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_update_response%20%3E%20(schema)>) NamespaceDeleteResponse = unknown [Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_delete_response%20%3E%20(schema)>)
NamespaceSearchResponse {chunks, query\_kind, errors, search\_query }
chunks: Array<Chunk> id: string Link to this property instance\_id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property
query\_kind: "text"| "image"| "multimodal" One of the following: "text" Link to this property "image" Link to this property "multimodal" Link to this property
Link to this property
errors?: Array<Error> instance\_id: string Link to this property message: string Link to this property
Link to this property search\_query?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_search_response%20%3E%20(schema)>)
NamespaceChatCompletionsResponse {choices, chunks, id, 3 more }
choices: Array<Choice>
message: Message {content, role }
content: string| Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >| string| null One of the following: string Link to this property
Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >
UnionMember0 {text, type } text: string minLength1 Link to this property type: "text" Link to this property
Link to this property
UnionMember1 {image\_url, type }
image\_url: ImageURL {url } url: string maxLength20971520 minLength1 Link to this property
Link to this property type: "image\_url" Link to this property
Link to this property
UnionMember2 {file, type }
file: File {filename, file\_data, file\_id } filename: string maxLength255 minLength1 Link to this property file\_data?: string maxLength13981144 minLength1 Link to this property file\_id?: string Link to this property
Link to this property type: "file" Link to this property
Link to this property
Link to this property string| null Link to this property
Link to this property
role: "system"| "developer"| "user"| 2 more One of the following: "system" Link to this property "developer" Link to this property "user" Link to this property "assistant" Link to this property "tool" Link to this property
Link to this property
Link to this property index?: number Link to this property
Link to this property
chunks: Array<Chunk> id: string Link to this property instance\_id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property id?: string Link to this property
errors?: Array<Error> instance\_id: string Link to this property message: string Link to this property
Link to this property model?: string Link to this property object?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces%20%3E%20(model)%20namespace_chat_completions_response%20%3E%20(schema)>) #### AI SearchNamespacesInstances ##### [List AI Search instances.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/list) client.aiSearch.namespaces.instances.list(stringname, InstanceListParams {account\_id, hostname, namespace, 5 more } params, RequestOptionsoptions?): V4PagePaginationArray< [InstanceListResponse]() {id, ai\_gateway\_id, ai\_search\_model, 42 more } > GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances ##### [Create an AI Search instance (Search for Agents requires the default namespace).](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/create) client.aiSearch.namespaces.instances.create(stringname, InstanceCreateParams {account\_id, id, ai\_gateway\_id, 27 more } params, RequestOptionsoptions?): [InstanceCreateResponse]() {id, created\_at, modified\_at, 36 more } POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances ##### [Get an AI Search instance.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/read) client.aiSearch.namespaces.instances.read(stringid, InstanceReadParams {account\_id, name } params, RequestOptionsoptions?): [InstanceReadResponse]() {id, created\_at, modified\_at, 36 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id} ##### [Update an AI Search instance (Search for Agents metadata requires the default namespace).](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/update) client.aiSearch.namespaces.instances.update(stringid, InstanceUpdateParams {account\_id, name, ai\_gateway\_id, 31 more } params, RequestOptionsoptions?): [InstanceUpdateResponse]() {id, created\_at, modified\_at, 36 more } PUT/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id} ##### [Delete an AI Search instance.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/delete) client.aiSearch.namespaces.instances.delete(stringid, InstanceDeleteParams {account\_id, name } params, RequestOptionsoptions?): [InstanceDeleteResponse]() {id, created\_at, modified\_at, 36 more } DELETE/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id} ##### [Get instance statistics.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/stats) client.aiSearch.namespaces.instances.stats(stringid, InstanceStatsParams {account\_id, name } params, RequestOptionsoptions?): [InstanceStatsResponse]() {completed, degraded, engine, 8 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/stats ##### [Search](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/search) client.aiSearch.namespaces.instances.search(stringid, InstanceSearchParams {account\_id, name, ai\_search\_options, 2 more } params, RequestOptionsoptions?): [InstanceSearchResponse]() {chunks, query\_kind, search\_query } POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/search ##### [Chat Completions](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/methods/chat_completions) client.aiSearch.namespaces.instances.chatCompletions(stringid, InstanceChatCompletionsParams {account\_id, name, messages, 3 more } params, RequestOptionsoptions?): [InstanceChatCompletionsResponse]() {choices, chunks, id, 2 more } POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/chat/completions ##### ModelsExpand Collapse
InstanceListResponse {id, ai\_gateway\_id, ai\_search\_model, 42 more } id: string Link to this property ai\_gateway\_id: string| null Link to this property ai\_search\_model: string| null Link to this property cache: boolean Link to this property
cache\_threshold: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "anything\_goes"| null 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: 600| 1800| 3600| 7 more 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: boolean Link to this property chunk\_overlap: number| null Link to this property chunk\_size: number| null Link to this property created\_at: string formatdate-time Link to this property created\_by: string| null Link to this property
custom\_metadata: Array<CustomMetadata>| null
data\_type: "text"| "number"| "boolean"| "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 Link to this property
Link to this property embedding\_model: string| null Link to this property enable: boolean Link to this property engine\_version: number Link to this property
fusion\_method: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property hybrid\_search\_enabled: boolean Link to this property
index\_method: IndexMethod {keyword, vector } keyword: boolean Link to this property vector: boolean Link to this property
Link to this property
indexing\_options: IndexingOptions| null
keyword\_tokenizer?: "porter"| "trigram" One of the following: "porter" Link to this property "trigram" Link to this property
Link to this property use\_ocr?: boolean Link to this property
Link to this property last\_activity: string| null formatdate-time Link to this property max\_num\_results: number| null Link to this property
metadata: Metadata| null created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_at: string formatdate-time Link to this property modified\_by: string| null Link to this property namespace: string Link to this property paused: boolean Link to this property public\_endpoint\_id: string| null Link to this property
public\_endpoint\_params: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Link to this property
Link to this property custom\_domains?: Array<string>| null Link to this property default\_domain\_enabled?: boolean Link to this property enabled?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Link to this property
Link to this property
Link to this property reranking: boolean Link to this property reranking\_model: string| null Link to this property
retrieval\_options: RetrievalOptions| null
boost\_by?: Array<BoostBy> field: string maxLength64 minLength1 Link to this property
dataType?: "number"| "datetime"| "text"| "boolean" One of the following: "number" Link to this property "datetime" Link to this property "text" Link to this property "boolean" Link to this property
Link to this property
direction?: "asc"| "desc"| "exists"| "not\_exists" 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
Link to this property
keyword\_match\_mode?: "and"| "or" One of the following: "and" Link to this property "or" Link to this property
Link to this property
Link to this property rewrite\_model: string| null Link to this property rewrite\_query: boolean Link to this property score\_threshold: number| null Link to this property source: string| null Link to this property
source\_params: SourceParams| null exclude\_items?: Array<string> Link to this property include\_items?: Array<string> Link to this property prefix?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {depth, include\_external\_links, include\_subdomains, 3 more } depth?: number maximum100000 minimum1 Link to this property include\_external\_links?: boolean Link to this property include\_subdomains?: boolean Link to this property limit?: number Maximum number of pages to crawl. New values are capped at 100000; instances configured before that cap may report a higher stored value, which the crawler clamps at run time. maximum100000 minimum1 Link to this property max\_age?: number maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "links" One of the following: "all" Link to this property "sitemaps" Link to this property "links" Link to this property
Link to this property
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> path: string maxLength200 minLength1 Link to this property selector: string maxLength200 minLength1 Link to this property
Link to this property include\_headers?: Record<string, string> Link to this property include\_images?: boolean Link to this property specific\_sitemaps?: Array<string> Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "discover" One of the following: "sitemap" Link to this property "discover" Link to this property
Link to this property
Link to this property
Link to this property status: string Link to this property summarization: boolean Link to this property summarization\_model: string| null Link to this property
sync\_interval: 900| 1800| 3600| 5 more 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 system\_prompt\_ai\_search: string| null Link to this property system\_prompt\_index\_summarization: string| null Link to this property system\_prompt\_rewrite\_query: string| null Link to this property token\_id: string| null Link to this property
type: "r2"| "web-crawler"| null 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.namespaces.instances%20%3E%20(model)%20instance_list_response%20%3E%20(schema)>)
InstanceCreateResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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.namespaces.instances%20%3E%20(model)%20instance_create_response%20%3E%20(schema)>)
InstanceReadResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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.namespaces.instances%20%3E%20(model)%20instance_read_response%20%3E%20(schema)>)
InstanceUpdateResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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.namespaces.instances%20%3E%20(model)%20instance_update_response%20%3E%20(schema)>)
InstanceDeleteResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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.namespaces.instances%20%3E%20(model)%20instance_delete_response%20%3E%20(schema)>)
InstanceStatsResponse {completed, degraded, engine, 8 more } completed?: number Link to this property degraded?: boolean True when status counts are unavailable (e.g. legacy stats query exceeded D1 statement-size limit). Counts are omitted in this case. Link to this property
engine?: Engine {r2, vectorize } Engine-specific metadata. Present only for managed (v3) instances.
r2?: R2 {metadataSizeBytes, objectCount, payloadSizeBytes } R2 bucket storage usage in bytes. metadataSizeBytes: number Link to this property objectCount: number Link to this property payloadSizeBytes: number Link to this property
Link to this property
vectorize?: Vectorize {dimensions, vectorsCount } Vectorize index metadata (dimensions, vector count). dimensions: number Link to this property vectorsCount: number Link to this property
Link to this property
Link to this property error?: number Link to this property file\_embed\_errors?: Record<string, unknown> Link to this property index\_source\_errors?: Record<string, unknown> Link to this property last\_activity?: string formatdate-time Link to this property outdated?: number Link to this property queued?: number Link to this property running?: number Link to this property skipped?: number Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_stats_response%20%3E%20(schema)>)
InstanceSearchResponse {chunks, query\_kind, search\_query }
chunks: Array<Chunk> id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property
query\_kind: "text"| "image"| "multimodal" One of the following: "text" Link to this property "image" Link to this property "multimodal" Link to this property
Link to this property search\_query?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_search_response%20%3E%20(schema)>)
InstanceChatCompletionsResponse {choices, chunks, id, 2 more }
choices: Array<Choice>
message: Message {content, role }
content: string| Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >| string| null One of the following: string Link to this property
Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >
UnionMember0 {text, type } text: string minLength1 Link to this property type: "text" Link to this property
Link to this property
UnionMember1 {image\_url, type }
image\_url: ImageURL {url } url: string maxLength20971520 minLength1 Link to this property
Link to this property type: "image\_url" Link to this property
Link to this property
UnionMember2 {file, type }
file: File {filename, file\_data, file\_id } filename: string maxLength255 minLength1 Link to this property file\_data?: string maxLength13981144 minLength1 Link to this property file\_id?: string Link to this property
Link to this property type: "file" Link to this property
Link to this property
Link to this property string| null Link to this property
Link to this property
role: "system"| "developer"| "user"| 2 more One of the following: "system" Link to this property "developer" Link to this property "user" Link to this property "assistant" Link to this property "tool" Link to this property
Link to this property
Link to this property index?: number Link to this property
Link to this property
chunks: Array<Chunk> id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property id?: string Link to this property model?: string Link to this property object?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances%20%3E%20(model)%20instance_chat_completions_response%20%3E%20(schema)>) #### AI SearchNamespacesInstancesJobs ##### [List Jobs](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/list) client.aiSearch.namespaces.instances.jobs.list(stringid, JobListParams {account\_id, name, page, per\_page } params, RequestOptionsoptions?): V4PagePaginationArray< [JobListResponse]() {id, source, description, 4 more } > GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs ##### [Create new job](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/create) client.aiSearch.namespaces.instances.jobs.create(stringid, JobCreateParams {account\_id, name, description } params, RequestOptionsoptions?): [JobCreateResponse]() {id, source, description, 4 more } POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs ##### [Get a Job Details](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/get) client.aiSearch.namespaces.instances.jobs.get(stringjobID, JobGetParams {account\_id, name, id } params, RequestOptionsoptions?): [JobGetResponse]() {id, source, description, 4 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id} ##### [Cancel an indexing job.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/update) client.aiSearch.namespaces.instances.jobs.update(stringjobID, JobUpdateParams {account\_id, name, id, action } params, RequestOptionsoptions?): [JobUpdateResponse]() {id, source, description, 4 more } PATCH/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id} ##### [List Job Logs](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/jobs/methods/logs) client.aiSearch.namespaces.instances.jobs.logs(stringjobID, JobLogsParams {account\_id, name, id, 2 more } params, RequestOptionsoptions?): [JobLogsResponse]() {id, created\_at, message, message\_type } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/jobs/{job\_id}/logs ##### ModelsExpand Collapse
JobListResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_list_response%20%3E%20(schema)>)
JobCreateResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_create_response%20%3E%20(schema)>)
JobGetResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_get_response%20%3E%20(schema)>)
JobUpdateResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_update_response%20%3E%20(schema)>)
JobLogsResponse = Array<JobLogsResponseItem> id: number Link to this property created\_at: number Link to this property message: string Link to this property message\_type: number Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.jobs%20%3E%20(model)%20job_logs_response%20%3E%20(schema)>) #### AI SearchNamespacesInstancesItems ##### [Items List.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/list) client.aiSearch.namespaces.instances.items.list(stringid, ItemListParams {account\_id, name, item\_id, 8 more } params, RequestOptionsoptions?): V4PagePaginationArray< [ItemListResponse]() {id, checksum, chunks\_count, 10 more } > GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items ##### [Upload Item.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/upload) client.aiSearch.namespaces.instances.items.upload(stringid, ItemUploadParams {account\_id, name, file } params, RequestOptionsoptions?): [ItemUploadResponse]() {id, checksum, chunks\_count, 11 more } POST/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items ##### [Create or Update Item.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/create_or_update) client.aiSearch.namespaces.instances.items.createOrUpdate(stringid, ItemCreateOrUpdateParams {account\_id, name, key, 2 more } params, RequestOptionsoptions?): [ItemCreateOrUpdateResponse]() {id, checksum, chunks\_count, 10 more } PUT/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items ##### [Get Item.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/get) client.aiSearch.namespaces.instances.items.get(stringitemID, ItemGetParams {account\_id, name, id } params, RequestOptionsoptions?): [ItemGetResponse]() {id, checksum, chunks\_count, 10 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id} ##### [Sync Item.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/sync) client.aiSearch.namespaces.instances.items.sync(stringitemID, ItemSyncParams {account\_id, name, id, 2 more } params, RequestOptionsoptions?): [ItemSyncResponse]() {id, checksum, chunks\_count, 10 more } PATCH/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id} ##### [Delete Item.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/delete) client.aiSearch.namespaces.instances.items.delete(stringitemID, ItemDeleteParams {account\_id, name, id } params, RequestOptionsoptions?): [ItemDeleteResponse]() {key } DELETE/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id} ##### [Download Item Content.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/download) client.aiSearch.namespaces.instances.items.download(stringitemID, ItemDownloadParams {account\_id, name, id } params, RequestOptionsoptions?): Response GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/download ##### [Item Logs.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/logs) client.aiSearch.namespaces.instances.items.logs(stringitemID, ItemLogsParams {account\_id, name, id, 2 more } params, RequestOptionsoptions?): [ItemLogsResponse]() {action, chunkCount, errorType, 4 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/logs ##### [List Item Chunks.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/namespaces/subresources/instances/subresources/items/methods/chunks) client.aiSearch.namespaces.instances.items.chunks(stringitemID, ItemChunksParams {account\_id, name, id, 2 more } params, RequestOptionsoptions?): [ItemChunksResponse]() {id, item, text, 2 more } GET/accounts/{account\_id}/ai-search/namespaces/{name}/instances/{id}/items/{item\_id}/chunks ##### ModelsExpand Collapse
ItemListResponse {id, checksum, chunks\_count, 10 more } id: string Link to this property checksum: string Link to this property chunks\_count: number| null Link to this property created\_at: string formatdate-time Link to this property file\_size: number| null Link to this property key: string Link to this property last\_seen\_at: string formatdate-time Link to this property
metadata: Record<string, string| number| boolean>| null Built-in, configured filterable, and retained source metadata for the item. One of the following: string Link to this property number Link to this property boolean Link to this property
Link to this property namespace: string Link to this property
next\_action: "INDEX"| "DELETE"| null One of the following: "INDEX" Link to this property "DELETE" Link to this property
Link to this property source\_id: string| null Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items. Link to this property
status: "queued"| "running"| "completed"| 3 more One of the following: "queued" Link to this property "running" Link to this property "completed" Link to this property "error" Link to this property "skipped" Link to this property "outdated" Link to this property
Link to this property error?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_list_response%20%3E%20(schema)>)
ItemUploadResponse {id, checksum, chunks\_count, 11 more } id: string Link to this property checksum: string Link to this property chunks\_count: number| null Link to this property created\_at: string formatdate-time Link to this property file\_size: number| null Link to this property key: string Link to this property last\_seen\_at: string formatdate-time Link to this property
metadata: Record<string, string| number| boolean>| null Built-in, configured filterable, and retained source metadata for the item. One of the following: string Link to this property number Link to this property boolean Link to this property
Link to this property namespace: string Link to this property
next\_action: "INDEX"| "DELETE"| null One of the following: "INDEX" Link to this property "DELETE" Link to this property
Link to this property source\_id: string| null Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items. Link to this property
status: "queued"| "running"| "completed"| 3 more One of the following: "queued" Link to this property "running" Link to this property "completed" Link to this property "error" Link to this property "skipped" Link to this property "outdated" Link to this property
Link to this property error?: string Link to this property
warnings?: Array<UnionMember0 {code, expected\_type, field } | UnionMember1 {code, field } > One of the following:
UnionMember0 {code, expected\_type, field } code: "custom\_metadata\_value\_not\_indexed" Link to this property
expected\_type: "text"| "number"| "boolean"| "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: string maxLength512 Link to this property
Link to this property
UnionMember1 {code, field } code: "custom\_metadata\_field\_not\_filterable" Link to this property field: string maxLength512 Link to this property
Link to this property
Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_upload_response%20%3E%20(schema)>)
ItemCreateOrUpdateResponse {id, checksum, chunks\_count, 10 more } id: string Link to this property checksum: string Link to this property chunks\_count: number| null Link to this property created\_at: string formatdate-time Link to this property file\_size: number| null Link to this property key: string Link to this property last\_seen\_at: string formatdate-time Link to this property
metadata: Record<string, string| number| boolean>| null Built-in, configured filterable, and retained source metadata for the item. One of the following: string Link to this property number Link to this property boolean Link to this property
Link to this property namespace: string Link to this property
next\_action: "INDEX"| "DELETE"| null One of the following: "INDEX" Link to this property "DELETE" Link to this property
Link to this property source\_id: string| null Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items. Link to this property
status: "queued"| "running"| "completed"| 3 more One of the following: "queued" Link to this property "running" Link to this property "completed" Link to this property "error" Link to this property "skipped" Link to this property "outdated" Link to this property
Link to this property error?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_create_or_update_response%20%3E%20(schema)>)
ItemGetResponse {id, checksum, chunks\_count, 10 more } id: string Link to this property checksum: string Link to this property chunks\_count: number| null Link to this property created\_at: string formatdate-time Link to this property file\_size: number| null Link to this property key: string Link to this property last\_seen\_at: string formatdate-time Link to this property
metadata: Record<string, string| number| boolean>| null Built-in, configured filterable, and retained source metadata for the item. One of the following: string Link to this property number Link to this property boolean Link to this property
Link to this property namespace: string Link to this property
next\_action: "INDEX"| "DELETE"| null One of the following: "INDEX" Link to this property "DELETE" Link to this property
Link to this property source\_id: string| null Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items. Link to this property
status: "queued"| "running"| "completed"| 3 more One of the following: "queued" Link to this property "running" Link to this property "completed" Link to this property "error" Link to this property "skipped" Link to this property "outdated" Link to this property
Link to this property error?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_get_response%20%3E%20(schema)>)
ItemSyncResponse {id, checksum, chunks\_count, 10 more } id: string Link to this property checksum: string Link to this property chunks\_count: number| null Link to this property created\_at: string formatdate-time Link to this property file\_size: number| null Link to this property key: string Link to this property last\_seen\_at: string formatdate-time Link to this property
metadata: Record<string, string| number| boolean>| null Built-in, configured filterable, and retained source metadata for the item. One of the following: string Link to this property number Link to this property boolean Link to this property
Link to this property namespace: string Link to this property
next\_action: "INDEX"| "DELETE"| null One of the following: "INDEX" Link to this property "DELETE" Link to this property
Link to this property source\_id: string| null Identifies which data source this item belongs to. “builtin” for uploaded files, “{type}:{source}” for external sources, null for legacy items. Link to this property
status: "queued"| "running"| "completed"| 3 more One of the following: "queued" Link to this property "running" Link to this property "completed" Link to this property "error" Link to this property "skipped" Link to this property "outdated" Link to this property
Link to this property error?: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_sync_response%20%3E%20(schema)>)
ItemDeleteResponse {key } key: string Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_delete_response%20%3E%20(schema)>)
ItemLogsResponse = Array<ItemLogsResponseItem> action: string Link to this property chunkCount: number| null Link to this property errorType: string| null Link to this property fileKey: string Link to this property message: string| null Link to this property processingTimeMs: number| null Link to this property timestamp: string formatdate-time Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_logs_response%20%3E%20(schema)>)
ItemChunksResponse = Array<ItemChunksResponseItem> id: string Link to this property
item: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property text: string Link to this property end\_byte?: number Link to this property start\_byte?: number Link to this property
[Link to this property](<#(resource)%20ai_search.namespaces.instances.items%20%3E%20(model)%20item_chunks_response%20%3E%20(schema)>) #### AI SearchInstances ##### [List AI Search instances.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/list) Deprecated client.aiSearch.instances.list(InstanceListParams {account\_id, hostname, namespace, 5 more } params, RequestOptionsoptions?): V4PagePaginationArray< [InstanceListResponse]() {id, ai\_gateway\_id, ai\_search\_model, 42 more } > GET/accounts/{account\_id}/ai-search/instances ##### [Create an AI Search instance (Search for Agents requires the default namespace).](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/create) Deprecated client.aiSearch.instances.create(InstanceCreateParams {account\_id, id, ai\_gateway\_id, 27 more } params, RequestOptionsoptions?): [InstanceCreateResponse]() {id, created\_at, modified\_at, 36 more } POST/accounts/{account\_id}/ai-search/instances ##### [Get an AI Search instance.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/read) Deprecated client.aiSearch.instances.read(stringid, InstanceReadParams {account\_id } params, RequestOptionsoptions?): [InstanceReadResponse]() {id, created\_at, modified\_at, 36 more } GET/accounts/{account\_id}/ai-search/instances/{id} ##### [Update an AI Search instance (Search for Agents metadata requires the default namespace).](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/update) Deprecated client.aiSearch.instances.update(stringid, InstanceUpdateParams {account\_id, ai\_gateway\_id, ai\_search\_model, 30 more } params, RequestOptionsoptions?): [InstanceUpdateResponse]() {id, created\_at, modified\_at, 36 more } PUT/accounts/{account\_id}/ai-search/instances/{id} ##### [Delete an AI Search instance.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/delete) Deprecated client.aiSearch.instances.delete(stringid, InstanceDeleteParams {account\_id } params, RequestOptionsoptions?): [InstanceDeleteResponse]() {id, created\_at, modified\_at, 36 more } DELETE/accounts/{account\_id}/ai-search/instances/{id} ##### [Get instance statistics.](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/stats) Deprecated client.aiSearch.instances.stats(stringid, InstanceStatsParams {account\_id } params, RequestOptionsoptions?): [InstanceStatsResponse]() {completed, degraded, engine, 8 more } GET/accounts/{account\_id}/ai-search/instances/{id}/stats ##### [Search](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/search) Deprecated client.aiSearch.instances.search(stringid, InstanceSearchParams {account\_id, ai\_search\_options, messages, query } params, RequestOptionsoptions?): [InstanceSearchResponse]() {chunks, query\_kind, search\_query } POST/accounts/{account\_id}/ai-search/instances/{id}/search ##### [Chat Completions](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/methods/chat_completions) Deprecated client.aiSearch.instances.chatCompletions(stringid, InstanceChatCompletionsParams {account\_id, messages, ai\_search\_options, 2 more } params, RequestOptionsoptions?): [InstanceChatCompletionsResponse]() {choices, chunks, id, 2 more } POST/accounts/{account\_id}/ai-search/instances/{id}/chat/completions ##### ModelsExpand Collapse
InstanceListResponse {id, ai\_gateway\_id, ai\_search\_model, 42 more } id: string Link to this property ai\_gateway\_id: string| null Link to this property ai\_search\_model: string| null Link to this property cache: boolean Link to this property
cache\_threshold: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "anything\_goes"| null 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: 600| 1800| 3600| 7 more 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: boolean Link to this property chunk\_overlap: number| null Link to this property chunk\_size: number| null Link to this property created\_at: string formatdate-time Link to this property created\_by: string| null Link to this property
custom\_metadata: Array<CustomMetadata>| null
data\_type: "text"| "number"| "boolean"| "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 Link to this property
Link to this property embedding\_model: string| null Link to this property enable: boolean Link to this property engine\_version: number Link to this property
fusion\_method: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property hybrid\_search\_enabled: boolean Link to this property
index\_method: IndexMethod {keyword, vector } keyword: boolean Link to this property vector: boolean Link to this property
Link to this property
indexing\_options: IndexingOptions| null
keyword\_tokenizer?: "porter"| "trigram" One of the following: "porter" Link to this property "trigram" Link to this property
Link to this property use\_ocr?: boolean Link to this property
Link to this property last\_activity: string| null formatdate-time Link to this property max\_num\_results: number| null Link to this property
metadata: Metadata| null created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_at: string formatdate-time Link to this property modified\_by: string| null Link to this property namespace: string Link to this property paused: boolean Link to this property public\_endpoint\_id: string| null Link to this property
public\_endpoint\_params: PublicEndpointParams| null authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Link to this property
Link to this property custom\_domains?: Array<string>| null Link to this property default\_domain\_enabled?: boolean Link to this property enabled?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Link to this property
Link to this property
Link to this property reranking: boolean Link to this property reranking\_model: string| null Link to this property
retrieval\_options: RetrievalOptions| null
boost\_by?: Array<BoostBy> field: string maxLength64 minLength1 Link to this property
dataType?: "number"| "datetime"| "text"| "boolean" One of the following: "number" Link to this property "datetime" Link to this property "text" Link to this property "boolean" Link to this property
Link to this property
direction?: "asc"| "desc"| "exists"| "not\_exists" 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
Link to this property
keyword\_match\_mode?: "and"| "or" One of the following: "and" Link to this property "or" Link to this property
Link to this property
Link to this property rewrite\_model: string| null Link to this property rewrite\_query: boolean Link to this property score\_threshold: number| null Link to this property source: string| null Link to this property
source\_params: SourceParams| null exclude\_items?: Array<string> Link to this property include\_items?: Array<string> Link to this property prefix?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {depth, include\_external\_links, include\_subdomains, 3 more } depth?: number maximum100000 minimum1 Link to this property include\_external\_links?: boolean Link to this property include\_subdomains?: boolean Link to this property limit?: number Maximum number of pages to crawl. New values are capped at 100000; instances configured before that cap may report a higher stored value, which the crawler clamps at run time. maximum100000 minimum1 Link to this property max\_age?: number maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "links" One of the following: "all" Link to this property "sitemaps" Link to this property "links" Link to this property
Link to this property
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> path: string maxLength200 minLength1 Link to this property selector: string maxLength200 minLength1 Link to this property
Link to this property include\_headers?: Record<string, string> Link to this property include\_images?: boolean Link to this property specific\_sitemaps?: Array<string> Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "discover" One of the following: "sitemap" Link to this property "discover" Link to this property
Link to this property
Link to this property
Link to this property status: string Link to this property summarization: boolean Link to this property summarization\_model: string| null Link to this property
sync\_interval: 900| 1800| 3600| 5 more 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 system\_prompt\_ai\_search: string| null Link to this property system\_prompt\_index\_summarization: string| null Link to this property system\_prompt\_rewrite\_query: string| null Link to this property token\_id: string| null Link to this property
type: "r2"| "web-crawler"| null 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(model)%20instance_list_response%20%3E%20(schema)>)
InstanceCreateResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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(model)%20instance_create_response%20%3E%20(schema)>)
InstanceReadResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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(model)%20instance_read_response%20%3E%20(schema)>)
InstanceUpdateResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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(model)%20instance_update_response%20%3E%20(schema)>)
InstanceDeleteResponse {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?: string| null Link to this property ai\_search\_model?: string| null 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?: boolean Link to this property
cache\_threshold?: "super\_strict\_match"| "close\_enough"| "flexible\_friend"| "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?: 600| 1800| 3600| 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?: number maximum30 minimum0 Link to this property chunk\_size?: number minimum64 Link to this property created\_by?: string| null Link to this property
custom\_metadata?: Array<CustomMetadata>
data\_type: "text"| "number"| "boolean"| "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?: string| null Link to this property enable?: boolean Link to this property engine\_version?: number Link to this property
fusion\_method?: "max"| "rrf" One of the following: "max" Link to this property "rrf" Link to this property
Link to this property Deprecatedhybrid\_search\_enabled?: 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?: IndexMethod {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?: IndexingOptions| null
keyword\_tokenizer?: "porter"| "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?: 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?: string| null formatdate-time Link to this property max\_num\_results?: number maximum50 minimum1 Link to this property
metadata?: Metadata {created\_from\_aisearch\_wizard, worker\_domain } created\_from\_aisearch\_wizard?: boolean Link to this property worker\_domain?: string Link to this property
Link to this property modified\_by?: string| null Link to this property namespace?: string| null Link to this property paused?: boolean Link to this property public\_endpoint\_id?: string| null Link to this property
public\_endpoint\_params?: PublicEndpointParams {authorized\_hosts, chat\_completions\_endpoint, custom\_domains, 5 more } authorized\_hosts?: Array<string> Link to this property
chat\_completions\_endpoint?: ChatCompletionsEndpoint {disabled } disabled?: boolean Disable chat completions endpoint for this public endpoint Link to this property
Link to this property custom\_domains?: Array<string>| null 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?: 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?: boolean Link to this property
mcp?: Mcp {description, disabled } description?: string Link to this property disabled?: boolean Disable MCP endpoint for this public endpoint Link to this property
Link to this property
rate\_limit?: RateLimit {period\_ms, requests, technique } period\_ms?: number maximum3600000 minimum60000 Link to this property requests?: number minimum1 Link to this property
technique?: "fixed"| "sliding" One of the following: "fixed" Link to this property "sliding" Link to this property
Link to this property
Link to this property
search\_endpoint?: SearchEndpoint {disabled } disabled?: boolean Disable search endpoint for this public endpoint Link to this property
Link to this property
Link to this property reranking?: boolean Link to this property reranking\_model?: string| null Link to this property
retrieval\_options?: RetrievalOptions| null
boost\_by?: Array<BoostBy> 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?: "asc"| "desc"| "exists"| "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
Link to this property
keyword\_match\_mode?: "and"| "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?: string| null 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?: boolean Link to this property score\_threshold?: number maximum1 minimum0 Link to this property source?: string| null Link to this property
source\_params?: SourceParams| null exclude\_items?: Array<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?: Array<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?: string Link to this property r2\_jurisdiction?: string Link to this property
web\_crawler?: WebCrawler {discover\_options, parse\_options, parse\_type }
discover\_options?: DiscoverOptions {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?: number Maximum link-follow depth from the seed URL. maximum100000 minimum1 Link to this property include\_external\_links?: 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?: boolean Follow links to subdomains of the source host. Link to this property limit?: number Maximum number of pages to crawl (1-100000). maximum100000 minimum1 Link to this property max\_age?: number Maximum content age in seconds to accept (0–604800). maximum604800 minimum0 Link to this property
source?: "all"| "sitemaps"| "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
Link to this property
parse\_options?: ParseOptions {content\_selector, include\_headers, include\_images, 2 more }
content\_selector?: Array<ContentSelector> 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?: Record<string, 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?: boolean Link to this property specific\_sitemaps?: Array<string> List of specific sitemap URLs to use for crawling. Only valid when parse\_type is ‘sitemap’. Link to this property use\_browser\_rendering?: boolean Link to this property
Link to this property
parse\_type?: "sitemap"| "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
Link to this property status?: string Link to this property
sync\_interval?: 900| 1800| 3600| 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?: string formatuuid Link to this property
type?: "r2"| "web-crawler"| null 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(model)%20instance_delete_response%20%3E%20(schema)>)
InstanceStatsResponse {completed, degraded, engine, 8 more } completed?: number Link to this property degraded?: boolean True when status counts are unavailable (e.g. legacy stats query exceeded D1 statement-size limit). Counts are omitted in this case. Link to this property
engine?: Engine {r2, vectorize } Engine-specific metadata. Present only for managed (v3) instances.
r2?: R2 {metadataSizeBytes, objectCount, payloadSizeBytes } R2 bucket storage usage in bytes. metadataSizeBytes: number Link to this property objectCount: number Link to this property payloadSizeBytes: number Link to this property
Link to this property
vectorize?: Vectorize {dimensions, vectorsCount } Vectorize index metadata (dimensions, vector count). dimensions: number Link to this property vectorsCount: number Link to this property
Link to this property
Link to this property error?: number Link to this property file\_embed\_errors?: Record<string, unknown> Link to this property index\_source\_errors?: Record<string, unknown> Link to this property last\_activity?: string formatdate-time Link to this property outdated?: number Link to this property queued?: number Link to this property running?: number Link to this property skipped?: number Link to this property
[Link to this property](<#(resource)%20ai_search.instances%20%3E%20(model)%20instance_stats_response%20%3E%20(schema)>)
InstanceSearchResponse {chunks, query\_kind, search\_query }
chunks: Array<Chunk> id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property
query\_kind: "text"| "image"| "multimodal" One of the following: "text" Link to this property "image" Link to this property "multimodal" Link to this property
Link to this property search\_query?: string Link to this property
[Link to this property](<#(resource)%20ai_search.instances%20%3E%20(model)%20instance_search_response%20%3E%20(schema)>)
InstanceChatCompletionsResponse {choices, chunks, id, 2 more }
choices: Array<Choice>
message: Message {content, role }
content: string| Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >| string| null One of the following: string Link to this property
Array<UnionMember0 {text, type } | UnionMember1 {image\_url, type } | UnionMember2 {file, type } >
UnionMember0 {text, type } text: string minLength1 Link to this property type: "text" Link to this property
Link to this property
UnionMember1 {image\_url, type }
image\_url: ImageURL {url } url: string maxLength20971520 minLength1 Link to this property
Link to this property type: "image\_url" Link to this property
Link to this property
UnionMember2 {file, type }
file: File {filename, file\_data, file\_id } filename: string maxLength255 minLength1 Link to this property file\_data?: string maxLength13981144 minLength1 Link to this property file\_id?: string Link to this property
Link to this property type: "file" Link to this property
Link to this property
Link to this property string| null Link to this property
Link to this property
role: "system"| "developer"| "user"| 2 more One of the following: "system" Link to this property "developer" Link to this property "user" Link to this property "assistant" Link to this property "tool" Link to this property
Link to this property
Link to this property index?: number Link to this property
Link to this property
chunks: Array<Chunk> id: string Link to this property score: number maximum1 minimum0 Link to this property text: string Link to this property type: string Link to this property
item?: Item {key, metadata, timestamp } key: string Link to this property metadata?: Record<string, unknown> Link to this property timestamp?: number Link to this property
Link to this property
scoring\_details?: ScoringDetails {fusion\_method, keyword\_rank, keyword\_score, 3 more }
fusion\_method?: "rrf"| "max" One of the following: "rrf" Link to this property "max" Link to this property
Link to this property keyword\_rank?: number Link to this property keyword\_score?: number minimum0 Link to this property reranking\_score?: number maximum1 minimum0 Link to this property vector\_rank?: number Link to this property vector\_score?: number maximum1 minimum0 Link to this property
Link to this property
Link to this property id?: string Link to this property model?: string Link to this property object?: string Link to this property
[Link to this property](<#(resource)%20ai_search.instances%20%3E%20(model)%20instance_chat_completions_response%20%3E%20(schema)>) #### AI SearchInstancesJobs ##### [List Jobs](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/subresources/jobs/methods/list) Deprecated client.aiSearch.instances.jobs.list(stringid, JobListParams {account\_id, page, per\_page } params, RequestOptionsoptions?): V4PagePaginationArray< [JobListResponse]() {id, source, description, 4 more } > GET/accounts/{account\_id}/ai-search/instances/{id}/jobs ##### [Create new job](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/subresources/jobs/methods/create) Deprecated client.aiSearch.instances.jobs.create(stringid, JobCreateParams {account\_id, description } params, RequestOptionsoptions?): [JobCreateResponse]() {id, source, description, 4 more } POST/accounts/{account\_id}/ai-search/instances/{id}/jobs ##### [Get a Job Details](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/subresources/jobs/methods/get) Deprecated client.aiSearch.instances.jobs.get(stringjobID, JobGetParams {account\_id, id } params, RequestOptionsoptions?): [JobGetResponse]() {id, source, description, 4 more } GET/accounts/{account\_id}/ai-search/instances/{id}/jobs/{job\_id} ##### [List Job Logs](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/instances/subresources/jobs/methods/logs) Deprecated client.aiSearch.instances.jobs.logs(stringjobID, JobLogsParams {account\_id, id, page, per\_page } params, RequestOptionsoptions?): [JobLogsResponse]() {id, created\_at, message, message\_type } GET/accounts/{account\_id}/ai-search/instances/{id}/jobs/{job\_id}/logs ##### ModelsExpand Collapse
JobListResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.instances.jobs%20%3E%20(model)%20job_list_response%20%3E%20(schema)>)
JobCreateResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.instances.jobs%20%3E%20(model)%20job_create_response%20%3E%20(schema)>)
JobGetResponse {id, source, description, 4 more } id: string Link to this property
source: "user"| "schedule" One of the following: "user" Link to this property "schedule" Link to this property
Link to this property description?: string Link to this property end\_reason?: string Link to this property ended\_at?: string Link to this property last\_seen\_at?: string Link to this property started\_at?: string Link to this property
[Link to this property](<#(resource)%20ai_search.instances.jobs%20%3E%20(model)%20job_get_response%20%3E%20(schema)>)
JobLogsResponse = Array<JobLogsResponseItem> id: number Link to this property created\_at: number Link to this property message: string Link to this property message\_type: number Link to this property
[Link to this property](<#(resource)%20ai_search.instances.jobs%20%3E%20(model)%20job_logs_response%20%3E%20(schema)>) #### AI SearchTokens ##### [List tokens](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/tokens/methods/list) client.aiSearch.tokens.list(TokenListParams {account\_id, page, per\_page, search } params, RequestOptionsoptions?): V4PagePaginationArray< [TokenListResponse]() {id, cf\_api\_id, created\_at, 6 more } > GET/accounts/{account\_id}/ai-search/tokens ##### [Create a token](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/tokens/methods/create) client.aiSearch.tokens.create(TokenCreateParams {account\_id, cf\_api\_id, cf\_api\_key, 2 more } params, RequestOptionsoptions?): [TokenCreateResponse]() {id, cf\_api\_id, created\_at, 6 more } POST/accounts/{account\_id}/ai-search/tokens ##### [Get a token](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/tokens/methods/read) client.aiSearch.tokens.read(stringid, TokenReadParams {account\_id } params, RequestOptionsoptions?): [TokenReadResponse]() {id, cf\_api\_id, created\_at, 6 more } GET/accounts/{account\_id}/ai-search/tokens/{id} ##### [Update a token](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/tokens/methods/update) client.aiSearch.tokens.update(stringid, TokenUpdateParams {account\_id, cf\_api\_id, cf\_api\_key, 2 more } params, RequestOptionsoptions?): [TokenUpdateResponse]() {id, cf\_api\_id, created\_at, 6 more } PUT/accounts/{account\_id}/ai-search/tokens/{id} ##### [Delete a token](https://developers.cloudflare.com/api/typescript/resources/ai_search/subresources/tokens/methods/delete) client.aiSearch.tokens.delete(stringid, TokenDeleteParams {account\_id } params, RequestOptionsoptions?): [TokenDeleteResponse]() DELETE/accounts/{account\_id}/ai-search/tokens/{id} ##### ModelsExpand Collapse
TokenListResponse {id, cf\_api\_id, created\_at, 6 more } id: string formatuuid Link to this property cf\_api\_id: string Link to this property created\_at: string formatdate-time Link to this property modified\_at: string formatdate-time Link to this property name: string Link to this property created\_by?: string| null Link to this property enabled?: boolean Link to this property legacy?: boolean Link to this property modified\_by?: string| null Link to this property
[Link to this property](<#(resource)%20ai_search.tokens%20%3E%20(model)%20token_list_response%20%3E%20(schema)>)
TokenCreateResponse {id, cf\_api\_id, created\_at, 6 more } id: string formatuuid Link to this property cf\_api\_id: string Link to this property created\_at: string formatdate-time Link to this property modified\_at: string formatdate-time Link to this property name: string Link to this property created\_by?: string| null Link to this property enabled?: boolean Link to this property legacy?: boolean Link to this property modified\_by?: string| null Link to this property
[Link to this property](<#(resource)%20ai_search.tokens%20%3E%20(model)%20token_create_response%20%3E%20(schema)>)
TokenReadResponse {id, cf\_api\_id, created\_at, 6 more } id: string formatuuid Link to this property cf\_api\_id: string Link to this property created\_at: string formatdate-time Link to this property modified\_at: string formatdate-time Link to this property name: string Link to this property created\_by?: string| null Link to this property enabled?: boolean Link to this property legacy?: boolean Link to this property modified\_by?: string| null Link to this property
[Link to this property](<#(resource)%20ai_search.tokens%20%3E%20(model)%20token_read_response%20%3E%20(schema)>)
TokenUpdateResponse {id, cf\_api\_id, created\_at, 6 more } id: string formatuuid Link to this property cf\_api\_id: string Link to this property created\_at: string formatdate-time Link to this property modified\_at: string formatdate-time Link to this property name: string Link to this property created\_by?: string| null Link to this property enabled?: boolean Link to this property legacy?: boolean Link to this property modified\_by?: string| null Link to this property
[Link to this property](<#(resource)%20ai_search.tokens%20%3E%20(model)%20token_update_response%20%3E%20(schema)>) TokenDeleteResponse = unknown [Link to this property](<#(resource)%20ai_search.tokens%20%3E%20(model)%20token_delete_response%20%3E%20(schema)>)