diff --git a/docs/openapi.json b/docs/openapi.json
index fd64a3ab..e6109188 100644
--- a/docs/openapi.json
+++ b/docs/openapi.json
@@ -556,6 +556,37 @@
           }
         }
       }
+    },
+    "/v1/models": {
+      "get": {
+        "tags": [
+          "Text Generation Inference"
+        ],
+        "summary": "Get model info",
+        "operationId": "openai_get_model_info",
+        "responses": {
+          "200": {
+            "description": "Served model info",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ModelInfo"
+                }
+              }
+            }
+          },
+          "404": {
+            "description": "Model not found",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "$ref": "#/components/schemas/ErrorResponse"
+                }
+              }
+            }
+          }
+        }
+      }
     }
   },
   "components": {
@@ -1747,6 +1778,35 @@
           }
         ]
       },
+      "ModelInfo": {
+        "type": "object",
+        "required": [
+          "id",
+          "object",
+          "created",
+          "owned_by"
+        ],
+        "properties": {
+          "created": {
+            "type": "integer",
+            "format": "int64",
+            "example": 1686935002,
+            "minimum": 0
+          },
+          "id": {
+            "type": "string",
+            "example": "gpt2"
+          },
+          "object": {
+            "type": "string",
+            "example": "model"
+          },
+          "owned_by": {
+            "type": "string",
+            "example": "openai"
+          }
+        }
+      },
       "OutputMessage": {
         "oneOf": [
           {
@@ -2094,4 +2154,4 @@
       "description": "Hugging Face Text Generation Inference API"
     }
   ]
-}
+}
\ No newline at end of file
diff --git a/router/src/server.rs b/router/src/server.rs
index 518b50e1..24003d95 100644
--- a/router/src/server.rs
+++ b/router/src/server.rs
@@ -121,9 +121,13 @@ async fn get_model_info(info: Extension<Info>) -> Json<Info> {
 get,
 tag = "Text Generation Inference",
 path = "/v1/models",
-responses((status = 200, description = "Served model info", body = ModelInfo))
+responses(
+(status = 200, description = "Served model info", body = ModelInfo),
+(status = 404, description = "Model not found", body = ErrorResponse),
+)
 )]
-#[instrument]
+#[instrument(skip(info))]
+/// Get model info
 async fn openai_get_model_info(info: Extension<Info>) -> Json<ModelsInfo> {
     Json(ModelsInfo {
         data: vec![ModelInfo {
@@ -1521,6 +1525,7 @@ chat_completions,
 completions,
 tokenize,
 metrics,
+openai_get_model_info,
 ),
 components(
 schemas(
@@ -1573,6 +1578,7 @@ ToolCall,
 Function,
 FunctionDefinition,
 ToolChoice,
+ModelInfo,
 )
 ),
 tags(