diff --git a/src/libs/Cohere/Generated/Cohere.CohereApi.Chat.g.cs b/src/libs/Cohere/Generated/Cohere.CohereApi.Chat.g.cs
index 0b1295d..15ee19d 100644
--- a/src/libs/Cohere/Generated/Cohere.CohereApi.Chat.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.CohereApi.Chat.g.cs
@@ -157,7 +157,7 @@ partial void ProcessChatResponseContent(
         ///  - AUTO_PRESERVE_ORDER: Azure, AWS Sagemaker/Bedrock, Private Deployments
         /// </param>
         /// <param name="connectors">
-        /// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.<br/>
+        /// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/overview-rag-connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.<br/>
         /// When specified, the model's reply will be enriched with information found by querying each of the connectors (RAG).<br/>
         /// Compatible Deployments: Cohere Platform
         /// </param>
diff --git a/src/libs/Cohere/Generated/Cohere.CohereApi.Generate.g.cs b/src/libs/Cohere/Generated/Cohere.CohereApi.Generate.g.cs
index eacb056..0cfc004 100644
--- a/src/libs/Cohere/Generated/Cohere.CohereApi.Generate.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.CohereApi.Generate.g.cs
@@ -134,7 +134,7 @@ partial void ProcessGenerateResponseContent(
         /// </param>
         /// <param name="maxTokens">
         /// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.<br/>
-        /// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token. See [BPE Tokens](/bpe-tokens-wiki) for more details.<br/>
+        /// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token.<br/>
         /// Can only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.
         /// </param>
         /// <param name="truncate">
diff --git a/src/libs/Cohere/Generated/Cohere.ConnectorsClient.DeleteConnector.g.cs b/src/libs/Cohere/Generated/Cohere.ConnectorsClient.DeleteConnector.g.cs
index d37677d..868b8ce 100644
--- a/src/libs/Cohere/Generated/Cohere.ConnectorsClient.DeleteConnector.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.ConnectorsClient.DeleteConnector.g.cs
@@ -25,7 +25,7 @@ partial void ProcessDeleteConnectorResponseContent(
 
         /// <summary>
         /// Delete a Connector<br/>
-        /// Delete a connector by ID. See ['Connectors'](https://docs.cohere.com/docs/connectors) for more information.
+        /// Delete a connector by ID. See ['Connectors'](https://docs.cohere.com/docs/overview-rag-connectors) for more information.
         /// </summary>
         /// <param name="id"></param>
         /// <param name="xClientName"></param>
diff --git a/src/libs/Cohere/Generated/Cohere.ConnectorsClient.GetConnector.g.cs b/src/libs/Cohere/Generated/Cohere.ConnectorsClient.GetConnector.g.cs
index 91959ed..f3ac3a9 100644
--- a/src/libs/Cohere/Generated/Cohere.ConnectorsClient.GetConnector.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.ConnectorsClient.GetConnector.g.cs
@@ -25,7 +25,7 @@ partial void ProcessGetConnectorResponseContent(
 
         /// <summary>
         /// Get a Connector<br/>
-        /// Retrieve a connector by ID. See ['Connectors'](https://docs.cohere.com/docs/connectors) for more information.
+        /// Retrieve a connector by ID. See ['Connectors'](https://docs.cohere.com/docs/overview-rag-connectors) for more information.
         /// </summary>
         /// <param name="id"></param>
         /// <param name="xClientName"></param>
diff --git a/src/libs/Cohere/Generated/Cohere.Models.ChatRequest.g.cs b/src/libs/Cohere/Generated/Cohere.Models.ChatRequest.g.cs
index 67006f7..a717310 100644
--- a/src/libs/Cohere/Generated/Cohere.Models.ChatRequest.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.Models.ChatRequest.g.cs
@@ -73,7 +73,7 @@ public sealed partial class ChatRequest
         public global::Cohere.ChatRequestPromptTruncation? PromptTruncation { get; set; }
 
         /// <summary>
-        /// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.<br/>
+        /// Accepts `{"id": "web-search"}`, and/or the `"id"` for a custom [connector](https://docs.cohere.com/docs/overview-rag-connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.<br/>
         /// When specified, the model's reply will be enriched with information found by querying each of the connectors (RAG).<br/>
         /// Compatible Deployments: Cohere Platform
         /// </summary>
diff --git a/src/libs/Cohere/Generated/Cohere.Models.GenerateRequest.g.cs b/src/libs/Cohere/Generated/Cohere.Models.GenerateRequest.g.cs
index a78a296..9c743e2 100644
--- a/src/libs/Cohere/Generated/Cohere.Models.GenerateRequest.g.cs
+++ b/src/libs/Cohere/Generated/Cohere.Models.GenerateRequest.g.cs
@@ -43,7 +43,7 @@ public sealed partial class GenerateRequest
 
         /// <summary>
         /// The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.<br/>
-        /// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token. See [BPE Tokens](/bpe-tokens-wiki) for more details.<br/>
+        /// This parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token.<br/>
         /// Can only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.
         /// </summary>
         [global::System.Text.Json.Serialization.JsonPropertyName("max_tokens")]
diff --git a/src/libs/Cohere/openapi.yaml b/src/libs/Cohere/openapi.yaml
index 90b6b82..0e79c34 100644
--- a/src/libs/Cohere/openapi.yaml
+++ b/src/libs/Cohere/openapi.yaml
@@ -87,7 +87,7 @@ paths:
                   type: array
                   items:
                     $ref: '#/components/schemas/ChatConnector'
-                  description: "Accepts `{\"id\": \"web-search\"}`, and/or the `\"id\"` for a custom [connector](https://docs.cohere.com/docs/connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.\n\nWhen specified, the model's reply will be enriched with information found by querying each of the connectors (RAG).\n\nCompatible Deployments: Cohere Platform\n"
+                  description: "Accepts `{\"id\": \"web-search\"}`, and/or the `\"id\"` for a custom [connector](https://docs.cohere.com/docs/overview-rag-connectors), if you've [created](https://docs.cohere.com/docs/creating-and-deploying-a-connector) one.\n\nWhen specified, the model's reply will be enriched with information found by querying each of the connectors (RAG).\n\nCompatible Deployments: Cohere Platform\n"
                   x-fern-audiences:
                     - public
                 search_queries_only:
@@ -1269,7 +1269,7 @@ paths:
                     - public
                 max_tokens:
                   type: integer
-                  description: "The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.\n\nThis parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token. See [BPE Tokens](/bpe-tokens-wiki) for more details.\n\nCan only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.\n"
+                  description: "The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.\n\nThis parameter is off by default, and if it's not specified, the model will continue generating until it emits an EOS completion token.\n\nCan only be set to `0` if `return_likelihoods` is set to `ALL` to get the likelihood of the prompt.\n"
                   writeOnly: true
                   x-fern-audiences:
                     - public
@@ -5556,7 +5556,7 @@ paths:
       tags:
         - /connectors
       summary: Get a Connector
-      description: 'Retrieve a connector by ID. See [''Connectors''](https://docs.cohere.com/docs/connectors) for more information.'
+      description: 'Retrieve a connector by ID. See [''Connectors''](https://docs.cohere.com/docs/overview-rag-connectors) for more information.'
       operationId: get-connector
       parameters:
         - name: id
@@ -5704,7 +5704,7 @@ paths:
       tags:
         - /connectors
       summary: Delete a Connector
-      description: 'Delete a connector by ID. See [''Connectors''](https://docs.cohere.com/docs/connectors) for more information.'
+      description: 'Delete a connector by ID. See [''Connectors''](https://docs.cohere.com/docs/overview-rag-connectors) for more information.'
       operationId: delete-connector
       parameters:
         - name: id