diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json
index 6c45fd480d..cfad1484e9 100644
--- a/output/openapi/elasticsearch-openapi.json
+++ b/output/openapi/elasticsearch-openapi.json
@@ -17573,6 +17573,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "CompletionRequestExample1": {
+                  "summary": "Completion task",
+                  "description": "Run `POST _inference/completion/openai_chat_completions` to perform a completion on the example question.",
+                  "value": "{\n  \"input\": \"What is Elastic?\"\n}"
+                }
               }
             }
           }
@@ -17584,6 +17591,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:CompletionInferenceResult"
+                },
+                "examples": {
+                  "CompletionResponseExample1": {
+                    "summary": "Completion task",
+                    "description": "A successful response from `POST _inference/completion/openai_chat_completions`.\n",
+                    "value": "{\n  \"completion\": [\n    {\n      \"result\": \"Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management.\"\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -18124,6 +18138,13 @@
                   "query",
                   "input"
                 ]
+              },
+              "examples": {
+                "RerankRequestExample1": {
+                  "summary": "Rerank task",
+                  "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.",
+                  "value": "{\n  \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n  \"query\": \"star wars main character\"\n}"
+                }
               }
             }
           }
@@ -18135,6 +18156,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:RerankedInferenceResult"
+                },
+                "examples": {
+                  "RerankResponseExample1": {
+                    "summary": "Rerank task",
+                    "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n",
+                    "value": "{\n  \"rerank\": [\n    {\n      \"index\": \"2\",\n      \"relevance_score\": \"0.011597361\",\n      \"text\": \"leia\"\n    },\n    {\n      \"index\": \"0\",\n      \"relevance_score\": \"0.006338922\",\n      \"text\": \"luke\"\n    },\n    {\n      \"index\": \"5\",\n      \"relevance_score\": \"0.0016166499\",\n      \"text\": \"star\"\n    },\n    {\n      \"index\": \"4\",\n      \"relevance_score\": \"0.0011695103\",\n      \"text\": \"r2d2\"\n    },\n    {\n      \"index\": \"1\",\n      \"relevance_score\": \"5.614787E-4\",\n      \"text\": \"like\"\n    },\n    {\n      \"index\": \"6\",\n      \"relevance_score\": \"3.7850367E-4\",\n      \"text\": \"wars\"\n    },\n    {\n      \"index\": \"3\",\n      \"relevance_score\": \"1.2508839E-5\",\n      \"text\": \"chewy\"\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -18200,6 +18228,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "SparseEmbeddingRequestExample1": {
+                  "summary": "Sparse embedding task",
+                  "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.",
+                  "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}"
+                }
               }
             }
           }
@@ -18211,6 +18246,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:SparseEmbeddingInferenceResult"
+                },
+                "examples": {
+                  "SparseEmbeddingResponseExample1": {
+                    "summary": "Sparse embedding task",
+                    "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n",
+                    "value": "{\n  \"sparse_embedding\": [\n    {\n      \"port\": 2.1259406,\n      \"sky\": 1.7073475,\n      \"color\": 1.6922266,\n      \"dead\": 1.6247464,\n      \"television\": 1.3525393,\n      \"above\": 1.2425821,\n      \"tuned\": 1.1440028,\n      \"colors\": 1.1218185,\n      \"tv\": 1.0111054,\n      \"ports\": 1.0067928,\n      \"poem\": 1.0042328,\n      \"channel\": 0.99471164,\n      \"tune\": 0.96235967,\n      \"scene\": 0.9020516\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -18350,6 +18392,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "TextEmbeddingRequestExample1": {
+                  "summary": "Text embedding task",
+                  "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,",
+                  "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n  \"task_settings\": {\n    \"input_type\": \"ingest\"\n  }\n}"
+                }
               }
             }
           }
@@ -18361,6 +18410,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:TextEmbeddingInferenceResult"
+                },
+                "examples": {
+                  "TextEmbeddingResponseExample1": {
+                    "summary": "Text embedding task",
+                    "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n",
+                    "value": "{\n  \"text_embedding\": [\n    {\n      \"embedding\": [\n        {\n          0.018569946,\n          -0.036895752,\n          0.01486969,\n          -0.0045204163,\n          -0.04385376,\n          0.0075950623,\n          0.04260254,\n          -0.004005432,\n          0.007865906,\n          0.030792236,\n          -0.050476074,\n          0.011795044,\n          -0.011642456,\n          -0.010070801\n        }\n      ]\n    }\n  ]\n}"
+                  }
                 }
               }
             }
diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json
index ef165f4ddf..909ba8972b 100644
--- a/output/openapi/elasticsearch-serverless-openapi.json
+++ b/output/openapi/elasticsearch-serverless-openapi.json
@@ -9395,6 +9395,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "CompletionRequestExample1": {
+                  "summary": "Completion task",
+                  "description": "Run `POST _inference/completion/openai_chat_completions` to perform a completion on the example question.",
+                  "value": "{\n  \"input\": \"What is Elastic?\"\n}"
+                }
               }
             }
           }
@@ -9406,6 +9413,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:CompletionInferenceResult"
+                },
+                "examples": {
+                  "CompletionResponseExample1": {
+                    "summary": "Completion task",
+                    "description": "A successful response from `POST _inference/completion/openai_chat_completions`.\n",
+                    "value": "{\n  \"completion\": [\n    {\n      \"result\": \"Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management.\"\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -9946,6 +9960,13 @@
                   "query",
                   "input"
                 ]
+              },
+              "examples": {
+                "RerankRequestExample1": {
+                  "summary": "Rerank task",
+                  "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.",
+                  "value": "{\n  \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n  \"query\": \"star wars main character\"\n}"
+                }
               }
             }
           }
@@ -9957,6 +9978,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:RerankedInferenceResult"
+                },
+                "examples": {
+                  "RerankResponseExample1": {
+                    "summary": "Rerank task",
+                    "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n",
+                    "value": "{\n  \"rerank\": [\n    {\n      \"index\": \"2\",\n      \"relevance_score\": \"0.011597361\",\n      \"text\": \"leia\"\n    },\n    {\n      \"index\": \"0\",\n      \"relevance_score\": \"0.006338922\",\n      \"text\": \"luke\"\n    },\n    {\n      \"index\": \"5\",\n      \"relevance_score\": \"0.0016166499\",\n      \"text\": \"star\"\n    },\n    {\n      \"index\": \"4\",\n      \"relevance_score\": \"0.0011695103\",\n      \"text\": \"r2d2\"\n    },\n    {\n      \"index\": \"1\",\n      \"relevance_score\": \"5.614787E-4\",\n      \"text\": \"like\"\n    },\n    {\n      \"index\": \"6\",\n      \"relevance_score\": \"3.7850367E-4\",\n      \"text\": \"wars\"\n    },\n    {\n      \"index\": \"3\",\n      \"relevance_score\": \"1.2508839E-5\",\n      \"text\": \"chewy\"\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -10022,6 +10050,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "SparseEmbeddingRequestExample1": {
+                  "summary": "Sparse embedding task",
+                  "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.",
+                  "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}"
+                }
               }
             }
           }
@@ -10033,6 +10068,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:SparseEmbeddingInferenceResult"
+                },
+                "examples": {
+                  "SparseEmbeddingResponseExample1": {
+                    "summary": "Sparse embedding task",
+                    "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n",
+                    "value": "{\n  \"sparse_embedding\": [\n    {\n      \"port\": 2.1259406,\n      \"sky\": 1.7073475,\n      \"color\": 1.6922266,\n      \"dead\": 1.6247464,\n      \"television\": 1.3525393,\n      \"above\": 1.2425821,\n      \"tuned\": 1.1440028,\n      \"colors\": 1.1218185,\n      \"tv\": 1.0111054,\n      \"ports\": 1.0067928,\n      \"poem\": 1.0042328,\n      \"channel\": 0.99471164,\n      \"tune\": 0.96235967,\n      \"scene\": 0.9020516\n    }\n  ]\n}"
+                  }
                 }
               }
             }
@@ -10098,6 +10140,13 @@
                 "required": [
                   "input"
                 ]
+              },
+              "examples": {
+                "TextEmbeddingRequestExample1": {
+                  "summary": "Text embedding task",
+                  "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,",
+                  "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n  \"task_settings\": {\n    \"input_type\": \"ingest\"\n  }\n}"
+                }
               }
             }
           }
@@ -10109,6 +10158,13 @@
               "application/json": {
                 "schema": {
                   "$ref": "#/components/schemas/inference._types:TextEmbeddingInferenceResult"
+                },
+                "examples": {
+                  "TextEmbeddingResponseExample1": {
+                    "summary": "Text embedding task",
+                    "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n",
+                    "value": "{\n  \"text_embedding\": [\n    {\n      \"embedding\": [\n        {\n          0.018569946,\n          -0.036895752,\n          0.01486969,\n          -0.0045204163,\n          -0.04385376,\n          0.0075950623,\n          0.04260254,\n          -0.004005432,\n          0.007865906,\n          0.030792236,\n          -0.050476074,\n          0.011795044,\n          -0.011642456,\n          -0.010070801\n        }\n      ]\n    }\n  ]\n}"
+                  }
                 }
               }
             }
diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json
index aa66f92b23..1f36cd49c2 100644
--- a/output/schema/schema-serverless.json
+++ b/output/schema/schema-serverless.json
@@ -26708,6 +26708,13 @@
         ]
       },
       "description": "Perform completion inference on the service",
+      "examples": {
+        "CompletionRequestExample1": {
+          "description": "Run `POST _inference/completion/openai_chat_completions` to perform a completion on the example question.",
+          "summary": "Completion task",
+          "value": "{\n  \"input\": \"What is Elastic?\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -26761,6 +26768,13 @@
           }
         }
       },
+      "examples": {
+        "CompletionResponseExample1": {
+          "description": "A successful response from `POST _inference/completion/openai_chat_completions`.\n",
+          "summary": "Completion task",
+          "value": "{\n  \"completion\": [\n    {\n      \"result\": \"Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management.\"\n    }\n  ]\n}"
+        }
+      },
       "kind": "response",
       "name": {
         "name": "Response",
@@ -27521,6 +27535,13 @@
         ]
       },
       "description": "Perform rereanking inference on the service",
+      "examples": {
+        "RerankRequestExample1": {
+          "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.",
+          "summary": "Rerank task",
+          "value": "{\n  \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n  \"query\": \"star wars main character\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -27574,6 +27595,13 @@
           }
         }
       },
+      "examples": {
+        "RerankResponseExample1": {
+          "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n",
+          "summary": "Rerank task",
+          "value": "{\n  \"rerank\": [\n    {\n      \"index\": \"2\",\n      \"relevance_score\": \"0.011597361\",\n      \"text\": \"leia\"\n    },\n    {\n      \"index\": \"0\",\n      \"relevance_score\": \"0.006338922\",\n      \"text\": \"luke\"\n    },\n    {\n      \"index\": \"5\",\n      \"relevance_score\": \"0.0016166499\",\n      \"text\": \"star\"\n    },\n    {\n      \"index\": \"4\",\n      \"relevance_score\": \"0.0011695103\",\n      \"text\": \"r2d2\"\n    },\n    {\n      \"index\": \"1\",\n      \"relevance_score\": \"5.614787E-4\",\n      \"text\": \"like\"\n    },\n    {\n      \"index\": \"6\",\n      \"relevance_score\": \"3.7850367E-4\",\n      \"text\": \"wars\"\n    },\n    {\n      \"index\": \"3\",\n      \"relevance_score\": \"1.2508839E-5\",\n      \"text\": \"chewy\"\n    }\n  ]\n}"
+        }
+      },
       "kind": "response",
       "name": {
         "name": "Response",
@@ -27630,6 +27658,13 @@
         ]
       },
       "description": "Perform sparse embedding inference on the service",
+      "examples": {
+        "SparseEmbeddingRequestExample1": {
+          "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.",
+          "summary": "Sparse embedding task",
+          "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -27683,6 +27718,13 @@
           }
         }
       },
+      "examples": {
+        "SparseEmbeddingResponseExample1": {
+          "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n",
+          "summary": "Sparse embedding task",
+          "value": "{\n  \"sparse_embedding\": [\n    {\n      \"port\": 2.1259406,\n      \"sky\": 1.7073475,\n      \"color\": 1.6922266,\n      \"dead\": 1.6247464,\n      \"television\": 1.3525393,\n      \"above\": 1.2425821,\n      \"tuned\": 1.1440028,\n      \"colors\": 1.1218185,\n      \"tv\": 1.0111054,\n      \"ports\": 1.0067928,\n      \"poem\": 1.0042328,\n      \"channel\": 0.99471164,\n      \"tune\": 0.96235967,\n      \"scene\": 0.9020516\n    }\n  ]\n}"
+        }
+      },
       "kind": "response",
       "name": {
         "name": "Response",
@@ -27739,6 +27781,13 @@
         ]
       },
       "description": "Perform text embedding inference on the service",
+      "examples": {
+        "TextEmbeddingRequestExample1": {
+          "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,",
+          "summary": "Text embedding task",
+          "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n  \"task_settings\": {\n    \"input_type\": \"ingest\"\n  }\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -27792,6 +27841,13 @@
           }
         }
       },
+      "examples": {
+        "TextEmbeddingResponseExample1": {
+          "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n",
+          "summary": "Text embedding task",
+          "value": "{\n  \"text_embedding\": [\n    {\n      \"embedding\": [\n        {\n          0.018569946,\n          -0.036895752,\n          0.01486969,\n          -0.0045204163,\n          -0.04385376,\n          0.0075950623,\n          0.04260254,\n          -0.004005432,\n          0.007865906,\n          0.030792236,\n          -0.050476074,\n          0.011795044,\n          -0.011642456,\n          -0.010070801\n        }\n      ]\n    }\n  ]\n}"
+        }
+      },
       "kind": "response",
       "name": {
         "name": "Response",
diff --git a/output/schema/schema.json b/output/schema/schema.json
index 8671596959..568c367605 100644
--- a/output/schema/schema.json
+++ b/output/schema/schema.json
@@ -150029,6 +150029,13 @@
         ]
       },
       "description": "Perform completion inference on the service",
+      "examples": {
+        "CompletionRequestExample1": {
+          "description": "Run `POST _inference/completion/openai_chat_completions` to perform a completion on the example question.",
+          "summary": "Completion task",
+          "value": "{\n  \"input\": \"What is Elastic?\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -150082,6 +150089,13 @@
           }
         }
       },
+      "examples": {
+        "CompletionResponseExample1": {
+          "description": "A successful response from `POST _inference/completion/openai_chat_completions`.\n",
+          "summary": "Completion task",
+          "value": "{\n  \"completion\": [\n    {\n      \"result\": \"Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management.\"\n    }\n  ]\n}"
+        }
+      },
       "name": {
         "name": "Response",
         "namespace": "inference.completion"
@@ -151310,6 +151324,13 @@
         ]
       },
       "description": "Perform rereanking inference on the service",
+      "examples": {
+        "RerankRequestExample1": {
+          "description": "Run `POST _inference/rerank/cohere_rerank` to perform reranking on the example input.",
+          "summary": "Rerank task",
+          "value": "{\n  \"input\": [\"luke\", \"like\", \"leia\", \"chewy\",\"r2d2\", \"star\", \"wars\"],\n  \"query\": \"star wars main character\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -151363,6 +151384,13 @@
           }
         }
       },
+      "examples": {
+        "RerankResponseExample1": {
+          "description": "A successful response from `POST _inference/rerank/cohere_rerank`.\n",
+          "summary": "Rerank task",
+          "value": "{\n  \"rerank\": [\n    {\n      \"index\": \"2\",\n      \"relevance_score\": \"0.011597361\",\n      \"text\": \"leia\"\n    },\n    {\n      \"index\": \"0\",\n      \"relevance_score\": \"0.006338922\",\n      \"text\": \"luke\"\n    },\n    {\n      \"index\": \"5\",\n      \"relevance_score\": \"0.0016166499\",\n      \"text\": \"star\"\n    },\n    {\n      \"index\": \"4\",\n      \"relevance_score\": \"0.0011695103\",\n      \"text\": \"r2d2\"\n    },\n    {\n      \"index\": \"1\",\n      \"relevance_score\": \"5.614787E-4\",\n      \"text\": \"like\"\n    },\n    {\n      \"index\": \"6\",\n      \"relevance_score\": \"3.7850367E-4\",\n      \"text\": \"wars\"\n    },\n    {\n      \"index\": \"3\",\n      \"relevance_score\": \"1.2508839E-5\",\n      \"text\": \"chewy\"\n    }\n  ]\n}"
+        }
+      },
       "name": {
         "name": "Response",
         "namespace": "inference.rerank"
@@ -151419,6 +151447,13 @@
         ]
       },
       "description": "Perform sparse embedding inference on the service",
+      "examples": {
+        "SparseEmbeddingRequestExample1": {
+          "description": "Run `POST _inference/sparse_embedding/my-elser-model` to perform sparse embedding on the example sentence.",
+          "summary": "Sparse embedding task",
+          "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\"\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -151472,6 +151507,13 @@
           }
         }
       },
+      "examples": {
+        "SparseEmbeddingResponseExample1": {
+          "description": "An abbreviated response from `POST _inference/sparse_embedding/my-elser-model`.\n",
+          "summary": "Sparse embedding task",
+          "value": "{\n  \"sparse_embedding\": [\n    {\n      \"port\": 2.1259406,\n      \"sky\": 1.7073475,\n      \"color\": 1.6922266,\n      \"dead\": 1.6247464,\n      \"television\": 1.3525393,\n      \"above\": 1.2425821,\n      \"tuned\": 1.1440028,\n      \"colors\": 1.1218185,\n      \"tv\": 1.0111054,\n      \"ports\": 1.0067928,\n      \"poem\": 1.0042328,\n      \"channel\": 0.99471164,\n      \"tune\": 0.96235967,\n      \"scene\": 0.9020516\n    }\n  ]\n}"
+        }
+      },
       "name": {
         "name": "Response",
         "namespace": "inference.sparse_embedding"
@@ -151630,6 +151672,13 @@
         ]
       },
       "description": "Perform text embedding inference on the service",
+      "examples": {
+        "TextEmbeddingRequestExample1": {
+          "description": "Run `POST _inference/text_embedding/my-cohere-endpoint` to perform text embedding on the example sentence using the Cohere integration,",
+          "summary": "Text embedding task",
+          "value": "{\n  \"input\": \"The sky above the port was the color of television tuned to a dead channel.\",\n  \"task_settings\": {\n    \"input_type\": \"ingest\"\n  }\n}"
+        }
+      },
       "inherits": {
         "type": {
           "name": "RequestBase",
@@ -151683,6 +151732,13 @@
           }
         }
       },
+      "examples": {
+        "TextEmbeddingResponseExample1": {
+          "description": "An abbreviated response from `POST _inference/text_embedding/my-cohere-endpoint`.\n",
+          "summary": "Text embedding task",
+          "value": "{\n  \"text_embedding\": [\n    {\n      \"embedding\": [\n        {\n          0.018569946,\n          -0.036895752,\n          0.01486969,\n          -0.0045204163,\n          -0.04385376,\n          0.0075950623,\n          0.04260254,\n          -0.004005432,\n          0.007865906,\n          0.030792236,\n          -0.050476074,\n          0.011795044,\n          -0.011642456,\n          -0.010070801\n        }\n      ]\n    }\n  ]\n}"
+        }
+      },
       "name": {
         "name": "Response",
         "namespace": "inference.text_embedding"
diff --git a/specification/inference/inference/examples/request/InferenceRequestExample1.yaml b/specification/inference/completion/examples/request/CompletionRequestExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/request/InferenceRequestExample1.yaml
rename to specification/inference/completion/examples/request/CompletionRequestExample1.yaml
diff --git a/specification/inference/inference/examples/response/InferenceResponseExample1.yaml b/specification/inference/completion/examples/response/CompletionResponseExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/response/InferenceResponseExample1.yaml
rename to specification/inference/completion/examples/response/CompletionResponseExample1.yaml
diff --git a/specification/inference/inference/examples/request/InferenceRequestExample2.yaml b/specification/inference/rerank/examples/request/RerankRequestExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/request/InferenceRequestExample2.yaml
rename to specification/inference/rerank/examples/request/RerankRequestExample1.yaml
diff --git a/specification/inference/inference/examples/response/InferenceResponseExample2.yaml b/specification/inference/rerank/examples/response/RerankResponseExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/response/InferenceResponseExample2.yaml
rename to specification/inference/rerank/examples/response/RerankResponseExample1.yaml
diff --git a/specification/inference/inference/examples/request/InferenceRequestExample3.yaml b/specification/inference/sparse_embedding/examples/request/SparseEmbeddingRequestExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/request/InferenceRequestExample3.yaml
rename to specification/inference/sparse_embedding/examples/request/SparseEmbeddingRequestExample1.yaml
diff --git a/specification/inference/inference/examples/response/InferenceResponseExample3.yaml b/specification/inference/sparse_embedding/examples/response/SparseEmbeddingResponseExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/response/InferenceResponseExample3.yaml
rename to specification/inference/sparse_embedding/examples/response/SparseEmbeddingResponseExample1.yaml
diff --git a/specification/inference/inference/examples/request/InferenceRequestExample4.yaml b/specification/inference/text_embedding/examples/request/TextEmbeddingRequestExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/request/InferenceRequestExample4.yaml
rename to specification/inference/text_embedding/examples/request/TextEmbeddingRequestExample1.yaml
diff --git a/specification/inference/inference/examples/response/InferenceResponseExample4.yaml b/specification/inference/text_embedding/examples/response/TextEmbeddingResponseExample1.yaml
similarity index 100%
rename from specification/inference/inference/examples/response/InferenceResponseExample4.yaml
rename to specification/inference/text_embedding/examples/response/TextEmbeddingResponseExample1.yaml