diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.chat_completion_unified.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.chat_completion_unified.json
new file mode 100644
index 0000000000000..98854625d0471
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.chat_completion_unified.json
@@ -0,0 +1,37 @@
+{
+  "inference.chat_completion_unified": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/chat-completion-inference.html",
+      "description": "Perform chat completion inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "text/event-stream"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/chat_completion/{inference_id}/_stream",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.completion.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.completion.json
new file mode 100644
index 0000000000000..6c753e59e3434
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.completion.json
@@ -0,0 +1,37 @@
+{
+  "inference.completion": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
+      "description": "Perform completion inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/completion/{inference_id}",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.get.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.get.json
index 14e7519c3796e..8887d9d0a1ebe 100644
--- a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.get.json
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.get.json
@@ -1,47 +1,49 @@
 {
-  "inference.get":{
-    "documentation":{
-      "url":"https://www.elastic.co/guide/en/elasticsearch/reference/master/get-inference-api.html",
-      "description":"Get an inference endpoint"
+  "inference.get": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/get-inference-api.html",
+      "description": "Get an inference endpoint"
     },
-    "stability":"stable",
-    "visibility":"public",
-    "headers":{
-      "accept": [ "application/json"]
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ]
     },
-    "url":{
-      "paths":[
+    "url": {
+      "paths": [
         {
-          "path":"/_inference",
-          "methods":[
+          "path": "/_inference",
+          "methods": [
             "GET"
           ]
         },
         {
-          "path":"/_inference/{inference_id}",
-          "methods":[
+          "path": "/_inference/{inference_id}",
+          "methods": [
             "GET"
           ],
-          "parts":{
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
             }
           }
         },
         {
-          "path":"/_inference/{task_type}/{inference_id}",
-          "methods":[
+          "path": "/_inference/{task_type}/{inference_id}",
+          "methods": [
             "GET"
           ],
-          "parts":{
-            "task_type":{
-              "type":"string",
-              "description":"The task type"
+          "parts": {
+            "task_type": {
+              "type": "string",
+              "description": "The task type"
             },
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
             }
           }
         }
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.inference.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.inference.json
deleted file mode 100644
index eb4c1268c28ca..0000000000000
--- a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.inference.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-  "inference.inference":{
-    "documentation":{
-      "url":"https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
-      "description":"Perform inference"
-    },
-    "stability":"stable",
-    "visibility":"public",
-    "headers":{
-      "accept": [ "application/json"],
-      "content_type": ["application/json"]
-    },
-    "url":{
-      "paths":[
-        {
-          "path":"/_inference/{inference_id}",
-          "methods":[
-            "POST"
-          ],
-          "parts":{
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
-            }
-          }
-        },
-        {
-          "path":"/_inference/{task_type}/{inference_id}",
-          "methods":[
-            "POST"
-          ],
-          "parts":{
-            "task_type":{
-              "type":"string",
-              "description":"The task type"
-            },
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
-            }
-          }
-        }
-      ]
-    },
-    "body":{
-      "description":"The inference payload"
-    }
-  }
-}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.put.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.put.json
index 411392fe39908..4879007724450 100644
--- a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.put.json
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.put.json
@@ -1,49 +1,53 @@
 {
-  "inference.put":{
-    "documentation":{
-      "url":"https://www.elastic.co/guide/en/elasticsearch/reference/master/put-inference-api.html",
-      "description":"Configure an inference endpoint for use in the Inference API"
+  "inference.put": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/put-inference-api.html",
+      "description": "Configure an inference endpoint for use in the Inference API"
     },
-    "stability":"stable",
-    "visibility":"public",
-    "headers":{
-      "accept": [ "application/json"],
-      "content_type": ["application/json"]
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ],
+      "content_type": [
+        "application/json"
+      ]
     },
-    "url":{
-      "paths":[
+    "url": {
+      "paths": [
         {
-          "path":"/_inference/{inference_id}",
-          "methods":[
+          "path": "/_inference/{inference_id}",
+          "methods": [
             "PUT"
           ],
-          "parts":{
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
             }
           }
         },
         {
-          "path":"/_inference/{task_type}/{inference_id}",
-          "methods":[
+          "path": "/_inference/{task_type}/{inference_id}",
+          "methods": [
             "PUT"
           ],
-          "parts":{
-            "task_type":{
-              "type":"string",
-              "description":"The task type"
+          "parts": {
+            "task_type": {
+              "type": "string",
+              "description": "The task type"
             },
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
             }
           }
         }
       ]
     },
-    "body":{
-      "description":"The inference endpoint's task and service settings"
+    "body": {
+      "description": "The inference endpoint's task and service settings"
     }
   }
 }
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.rerank.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.rerank.json
new file mode 100644
index 0000000000000..c08a51a8b9b98
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.rerank.json
@@ -0,0 +1,37 @@
+{
+  "inference.rerank": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
+      "description": "Perform reranking inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/rerank/{inference_id}",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.sparse_embedding.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.sparse_embedding.json
new file mode 100644
index 0000000000000..90ebb6e6dc4c2
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.sparse_embedding.json
@@ -0,0 +1,37 @@
+{
+  "inference.sparse_embedding": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
+      "description": "Perform sparse embedding inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/sparse_embedding/{inference_id}",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_completion.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_completion.json
new file mode 100644
index 0000000000000..a1d770c46305b
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_completion.json
@@ -0,0 +1,37 @@
+{
+  "inference.stream_completion": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-stream-inference-api.html",
+      "description": "Perform streaming inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "text/event-stream"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/completion/{inference_id}/_stream",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_inference.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_inference.json
deleted file mode 100644
index 493306e10d5c7..0000000000000
--- a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.stream_inference.json
+++ /dev/null
@@ -1,49 +0,0 @@
-{
-  "inference.stream_inference":{
-    "documentation":{
-      "url":"https://www.elastic.co/guide/en/elasticsearch/reference/master/post-stream-inference-api.html",
-      "description":"Perform streaming inference"
-    },
-    "stability":"stable",
-    "visibility":"public",
-    "headers":{
-      "accept": [ "text/event-stream"],
-      "content_type": ["application/json"]
-    },
-    "url":{
-      "paths":[
-        {
-          "path":"/_inference/{inference_id}/_stream",
-          "methods":[
-            "POST"
-          ],
-          "parts":{
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
-            }
-          }
-        },
-        {
-          "path":"/_inference/{task_type}/{inference_id}/_stream",
-          "methods":[
-            "POST"
-          ],
-          "parts":{
-            "task_type":{
-              "type":"string",
-              "description":"The task type"
-            },
-            "inference_id":{
-              "type":"string",
-              "description":"The inference Id"
-            }
-          }
-        }
-      ]
-    },
-    "body":{
-      "description":"The inference payload"
-    }
-  }
-}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.text_embedding.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.text_embedding.json
new file mode 100644
index 0000000000000..309a1d80b7416
--- /dev/null
+++ b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.text_embedding.json
@@ -0,0 +1,37 @@
+{
+  "inference.text_embedding": {
+    "documentation": {
+      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/post-inference-api.html",
+      "description": "Perform text embedding inference"
+    },
+    "stability": "stable",
+    "visibility": "public",
+    "headers": {
+      "accept": [
+        "application/json"
+      ],
+      "content_type": [
+        "application/json"
+      ]
+    },
+    "url": {
+      "paths": [
+        {
+          "path": "/_inference/text_embedding/{inference_id}",
+          "methods": [
+            "POST"
+          ],
+          "parts": {
+            "inference_id": {
+              "type": "string",
+              "description": "The inference Id"
+            }
+          }
+        }
+      ]
+    },
+    "body": {
+      "description": "The inference payload"
+    }
+  }
+}
diff --git a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.unified_inference.json b/rest-api-spec/src/main/resources/rest-api-spec/api/inference.unified_inference.json
deleted file mode 100644
index 84182d19f8825..0000000000000
--- a/rest-api-spec/src/main/resources/rest-api-spec/api/inference.unified_inference.json
+++ /dev/null
@@ -1,45 +0,0 @@
-{
-  "inference.unified_inference": {
-    "documentation": {
-      "url": "https://www.elastic.co/guide/en/elasticsearch/reference/master/unified-inference-api.html",
-      "description": "Perform inference using the Unified Schema"
-    },
-    "stability": "stable",
-    "visibility": "public",
-    "headers": {
-      "accept": ["text/event-stream"],
-      "content_type": ["application/json"]
-    },
-    "url": {
-      "paths": [
-        {
-          "path": "/_inference/{inference_id}/_unified",
-          "methods": ["POST"],
-          "parts": {
-            "inference_id": {
-              "type": "string",
-              "description": "The inference Id"
-            }
-          }
-        },
-        {
-          "path": "/_inference/{task_type}/{inference_id}/_unified",
-          "methods": ["POST"],
-          "parts": {
-            "task_type": {
-              "type": "string",
-              "description": "The task type"
-            },
-            "inference_id": {
-              "type": "string",
-              "description": "The inference Id"
-            }
-          }
-        }
-      ]
-    },
-    "body": {
-      "description": "The inference payload"
-    }
-  }
-}
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ChatCompletionInput.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ChatCompletionInput.java
index 928da95d9c2f0..58c952b9c556a 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ChatCompletionInput.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/ChatCompletionInput.java
@@ -7,6 +7,8 @@
 
 package org.elasticsearch.xpack.inference.external.http.sender;
 
+import org.elasticsearch.inference.TaskType;
+
 import java.util.List;
 import java.util.Objects;
 
@@ -15,7 +17,7 @@
  * The main difference between this class and {@link UnifiedChatInput} is this should only be used for
  * {@link org.elasticsearch.inference.TaskType#COMPLETION} originating through the
  * {@link org.elasticsearch.inference.InferenceService#infer} code path. These are requests sent to the
- * API without using the <code>_unified</code> route.
+ * API without using the {@link TaskType#CHAT_COMPLETION} task type.
  */
 public class ChatCompletionInput extends InferenceInputs {
     private final List<String> input;
diff --git a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/UnifiedChatInput.java b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/UnifiedChatInput.java
index fceec7c431182..f4f0511a4cc1b 100644
--- a/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/UnifiedChatInput.java
+++ b/x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/external/http/sender/UnifiedChatInput.java
@@ -10,6 +10,7 @@
 import org.elasticsearch.action.ActionListener;
 import org.elasticsearch.core.TimeValue;
 import org.elasticsearch.inference.Model;
+import org.elasticsearch.inference.TaskType;
 import org.elasticsearch.inference.UnifiedCompletionRequest;
 
 import java.util.List;
@@ -20,7 +21,7 @@
  * The main difference between this class and {@link ChatCompletionInput} is this should only be used for
  * {@link org.elasticsearch.inference.TaskType#COMPLETION} originating through the
  * {@link org.elasticsearch.inference.InferenceService#unifiedCompletionInfer(Model, UnifiedCompletionRequest, TimeValue, ActionListener)}
- * code path. These are requests sent to the API with the <code>_unified</code> route.
+ * code path. These are requests sent to the API with the <code>_stream</code> route and {@link TaskType#CHAT_COMPLETION}.
  */
 public class UnifiedChatInput extends InferenceInputs {
     private final UnifiedCompletionRequest request;
diff --git a/x-pack/plugin/src/yamlRestTest/resources/rest-api-spec/test/inference/inference_crud.yml b/x-pack/plugin/src/yamlRestTest/resources/rest-api-spec/test/inference/inference_crud.yml
index cdc69001d33ef..62a49422079b8 100644
--- a/x-pack/plugin/src/yamlRestTest/resources/rest-api-spec/test/inference/inference_crud.yml
+++ b/x-pack/plugin/src/yamlRestTest/resources/rest-api-spec/test/inference/inference_crud.yml
@@ -25,18 +25,3 @@
             }
           }
   - match: { error.reason: "Unknown task_type [bad]" }
-
----
-"Test inference with bad task type":
-  - do:
-      catch: bad_request
-      inference.inference:
-        task_type: bad
-        inference_id: elser_model
-        body: >
-          {
-            "input": "important text"
-          }
-  - match: { error.reason: "Unknown task_type [bad]" }
-
-