diff --git a/docs/docs.go b/docs/docs.go
index 6248bd8..0448820 100644
--- a/docs/docs.go
+++ b/docs/docs.go
@@ -21,6 +21,11 @@ const docTemplate = `{
     "paths": {
         "/instances": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of all instances managed by the server",
                 "tags": [
                     "instances"
@@ -47,6 +52,11 @@ const docTemplate = `{
         },
         "/instances/{name}": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the details of a specific instance by name",
                 "tags": [
                     "instances"
@@ -83,6 +93,11 @@ const docTemplate = `{
                 }
             },
             "put": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Updates the configuration of a specific instance by name",
                 "consumes": [
                     "application/json"
@@ -131,6 +146,11 @@ const docTemplate = `{
                 }
             },
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Creates a new instance with the provided configuration options",
                 "consumes": [
                     "application/json"
@@ -179,6 +199,11 @@ const docTemplate = `{
                 }
             },
             "delete": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Stops and removes a specific instance by name",
                 "tags": [
                     "instances"
@@ -214,6 +239,11 @@ const docTemplate = `{
         },
         "/instances/{name}/logs": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the logs from a specific instance by name with optional line limit",
                 "tags": [
                     "instances"
@@ -258,6 +288,11 @@ const docTemplate = `{
         },
         "/instances/{name}/proxy": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Forwards HTTP requests to the llama-server instance running on a specific port",
                 "tags": [
                     "instances"
@@ -297,6 +332,11 @@ const docTemplate = `{
                 }
             },
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Forwards HTTP requests to the llama-server instance running on a specific port",
                 "tags": [
                     "instances"
@@ -338,6 +378,11 @@ const docTemplate = `{
         },
         "/instances/{name}/restart": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Restarts a specific instance by name",
                 "tags": [
                     "instances"
@@ -376,6 +421,11 @@ const docTemplate = `{
         },
         "/instances/{name}/start": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Starts a specific instance by name",
                 "tags": [
                     "instances"
@@ -414,6 +464,11 @@ const docTemplate = `{
         },
         "/instances/{name}/stop": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Stops a specific instance by name",
                 "tags": [
                     "instances"
@@ -452,6 +507,11 @@ const docTemplate = `{
         },
         "/server/devices": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of available devices for the llama server",
                 "tags": [
                     "server"
@@ -475,6 +535,11 @@ const docTemplate = `{
         },
         "/server/help": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the help text for the llama server command",
                 "tags": [
                     "server"
@@ -498,6 +563,11 @@ const docTemplate = `{
         },
         "/server/version": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the version of the llama server command",
                 "tags": [
                     "server"
@@ -521,7 +591,12 @@ const docTemplate = `{
         },
         "/v1/": {
             "post": {
-                "description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body",
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
+                "description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body. Requires API key authentication via the ` + "`" + `Authorization` + "`" + ` header.",
                 "consumes": [
                     "application/json"
                 ],
@@ -550,6 +625,11 @@ const docTemplate = `{
         },
         "/v1/models": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of instances in a format compatible with OpenAI API",
                 "tags": [
                     "openai"
diff --git a/docs/swagger.json b/docs/swagger.json
index ae75018..87168b7 100644
--- a/docs/swagger.json
+++ b/docs/swagger.json
@@ -14,6 +14,11 @@
     "paths": {
         "/instances": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of all instances managed by the server",
                 "tags": [
                     "instances"
@@ -40,6 +45,11 @@
         },
         "/instances/{name}": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the details of a specific instance by name",
                 "tags": [
                     "instances"
@@ -76,6 +86,11 @@
                 }
             },
             "put": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Updates the configuration of a specific instance by name",
                 "consumes": [
                     "application/json"
@@ -124,6 +139,11 @@
                 }
             },
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Creates a new instance with the provided configuration options",
                 "consumes": [
                     "application/json"
@@ -172,6 +192,11 @@
                 }
             },
             "delete": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Stops and removes a specific instance by name",
                 "tags": [
                     "instances"
@@ -207,6 +232,11 @@
         },
         "/instances/{name}/logs": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the logs from a specific instance by name with optional line limit",
                 "tags": [
                     "instances"
@@ -251,6 +281,11 @@
         },
         "/instances/{name}/proxy": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Forwards HTTP requests to the llama-server instance running on a specific port",
                 "tags": [
                     "instances"
@@ -290,6 +325,11 @@
                 }
             },
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Forwards HTTP requests to the llama-server instance running on a specific port",
                 "tags": [
                     "instances"
@@ -331,6 +371,11 @@
         },
         "/instances/{name}/restart": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Restarts a specific instance by name",
                 "tags": [
                     "instances"
@@ -369,6 +414,11 @@
         },
         "/instances/{name}/start": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Starts a specific instance by name",
                 "tags": [
                     "instances"
@@ -407,6 +457,11 @@
         },
         "/instances/{name}/stop": {
             "post": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Stops a specific instance by name",
                 "tags": [
                     "instances"
@@ -445,6 +500,11 @@
         },
         "/server/devices": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of available devices for the llama server",
                 "tags": [
                     "server"
@@ -468,6 +528,11 @@
         },
         "/server/help": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the help text for the llama server command",
                 "tags": [
                     "server"
@@ -491,6 +556,11 @@
         },
         "/server/version": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns the version of the llama server command",
                 "tags": [
                     "server"
@@ -514,7 +584,12 @@
         },
         "/v1/": {
             "post": {
-                "description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body",
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
+                "description": "Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body. Requires API key authentication via the `Authorization` header.",
                 "consumes": [
                     "application/json"
                 ],
@@ -543,6 +618,11 @@
         },
         "/v1/models": {
             "get": {
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ],
                 "description": "Returns a list of instances in a format compatible with OpenAI API",
                 "tags": [
                     "openai"
diff --git a/docs/swagger.yaml b/docs/swagger.yaml
index cf45768..d6a7433 100644
--- a/docs/swagger.yaml
+++ b/docs/swagger.yaml
@@ -399,6 +399,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: List all instances
       tags:
       - instances
@@ -422,6 +424,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Delete an instance
       tags:
       - instances
@@ -446,6 +450,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Get details of a specific instance
       tags:
       - instances
@@ -478,6 +484,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Create and start a new instance
       tags:
       - instances
@@ -510,6 +518,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Update an instance's configuration
       tags:
       - instances
@@ -540,6 +550,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Get logs from a specific instance
       tags:
       - instances
@@ -568,6 +580,8 @@ paths:
           description: Instance is not running
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Proxy requests to a specific instance
       tags:
       - instances
@@ -595,6 +609,8 @@ paths:
           description: Instance is not running
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Proxy requests to a specific instance
       tags:
       - instances
@@ -620,6 +636,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Restart a running instance
       tags:
       - instances
@@ -645,6 +663,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Start a stopped instance
       tags:
       - instances
@@ -670,6 +690,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Stop a running instance
       tags:
       - instances
@@ -685,6 +707,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: List available devices for llama server
       tags:
       - server
@@ -700,6 +724,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Get help for llama server
       tags:
       - server
@@ -715,6 +741,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: Get version of llama server
       tags:
       - server
@@ -723,7 +751,8 @@ paths:
       consumes:
       - application/json
       description: Handles all POST requests to /v1/*, routing to the appropriate
-        instance based on the request body
+        instance based on the request body. Requires API key authentication via the
+        `Authorization` header.
       responses:
         "200":
           description: OpenAI response
@@ -735,6 +764,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: OpenAI-compatible proxy endpoint
       tags:
       - openai
@@ -751,6 +782,8 @@ paths:
           description: Internal Server Error
           schema:
             type: string
+      security:
+      - ApiKeyAuth: []
       summary: List instances in OpenAI-compatible format
       tags:
       - openai
diff --git a/pkg/handlers.go b/pkg/handlers.go
index afaee99..fe2088b 100644
--- a/pkg/handlers.go
+++ b/pkg/handlers.go
@@ -29,6 +29,7 @@ func NewHandler(im InstanceManager, config Config) *Handler {
 // @Summary Get help for llama server
 // @Description Returns the help text for the llama server command
 // @Tags server
+// @Security ApiKeyAuth
 // @Produces text/plain
 // @Success 200 {string} string "Help text"
 // @Failure 500 {string} string "Internal Server Error"
@@ -50,6 +51,7 @@ func (h *Handler) HelpHandler() http.HandlerFunc {
 // @Summary Get version of llama server
 // @Description Returns the version of the llama server command
 // @Tags server
+// @Security ApiKeyAuth
 // @Produces text/plain
 // @Success 200 {string} string "Version information"
 // @Failure 500 {string} string "Internal Server Error"
@@ -71,6 +73,7 @@ func (h *Handler) VersionHandler() http.HandlerFunc {
 // @Summary List available devices for llama server
 // @Description Returns a list of available devices for the llama server
 // @Tags server
+// @Security ApiKeyAuth
 // @Produces text/plain
 // @Success 200 {string} string "List of devices"
 // @Failure 500 {string} string "Internal Server Error"
@@ -92,6 +95,7 @@ func (h *Handler) ListDevicesHandler() http.HandlerFunc {
 // @Summary List all instances
 // @Description Returns a list of all instances managed by the server
 // @Tags instances
+// @Security ApiKeyAuth
 // @Produces json
 // @Success 200 {array} Instance "List of instances"
 // @Failure 500 {string} string "Internal Server Error"
@@ -116,6 +120,7 @@ func (h *Handler) ListInstances() http.HandlerFunc {
 // @Summary Create and start a new instance
 // @Description Creates a new instance with the provided configuration options
 // @Tags instances
+// @Security ApiKeyAuth
 // @Accept json
 // @Produces json
 // @Param name path string true "Instance Name"
@@ -157,6 +162,7 @@ func (h *Handler) CreateInstance() http.HandlerFunc {
 // @Summary Get details of a specific instance
 // @Description Returns the details of a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Produces json
 // @Param name path string true "Instance Name"
 // @Success 200 {object} Instance "Instance details"
@@ -189,6 +195,7 @@ func (h *Handler) GetInstance() http.HandlerFunc {
 // @Summary Update an instance's configuration
 // @Description Updates the configuration of a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Accept json
 // @Produces json
 // @Param name path string true "Instance Name"
@@ -229,6 +236,7 @@ func (h *Handler) UpdateInstance() http.HandlerFunc {
 // @Summary Start a stopped instance
 // @Description Starts a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Produces json
 // @Param name path string true "Instance Name"
 // @Success 200 {object} Instance "Started instance details"
@@ -261,6 +269,7 @@ func (h *Handler) StartInstance() http.HandlerFunc {
 // @Summary Stop a running instance
 // @Description Stops a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Produces json
 // @Param name path string true "Instance Name"
 // @Success 200 {object} Instance "Stopped instance details"
@@ -293,6 +302,7 @@ func (h *Handler) StopInstance() http.HandlerFunc {
 // @Summary Restart a running instance
 // @Description Restarts a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Produces json
 // @Param name path string true "Instance Name"
 // @Success 200 {object} Instance "Restarted instance details"
@@ -325,6 +335,7 @@ func (h *Handler) RestartInstance() http.HandlerFunc {
 // @Summary Delete an instance
 // @Description Stops and removes a specific instance by name
 // @Tags instances
+// @Security ApiKeyAuth
 // @Param name path string true "Instance Name"
 // @Success 204 "No Content"
 // @Failure 400 {string} string "Invalid name format"
@@ -351,6 +362,7 @@ func (h *Handler) DeleteInstance() http.HandlerFunc {
 // @Summary Get logs from a specific instance
 // @Description Returns the logs from a specific instance by name with optional line limit
 // @Tags instances
+// @Security ApiKeyAuth
 // @Param name path string true "Instance Name"
 // @Param lines query string false "Number of lines to retrieve (default: all lines)"
 // @Produces text/plain
@@ -398,6 +410,7 @@ func (h *Handler) GetInstanceLogs() http.HandlerFunc {
 // @Summary Proxy requests to a specific instance
 // @Description Forwards HTTP requests to the llama-server instance running on a specific port
 // @Tags instances
+// @Security ApiKeyAuth
 // @Param name path string true "Instance Name"
 // @Success 200 "Request successfully proxied to instance"
 // @Failure 400 {string} string "Invalid name format"
@@ -462,6 +475,7 @@ func (h *Handler) ProxyToInstance() http.HandlerFunc {
 // @Summary List instances in OpenAI-compatible format
 // @Description Returns a list of instances in a format compatible with OpenAI API
 // @Tags openai
+// @Security ApiKeyAuth
 // @Produces json
 // @Success 200 {object} OpenAIListInstancesResponse "List of OpenAI-compatible instances"
 // @Failure 500 {string} string "Internal Server Error"
@@ -499,8 +513,9 @@ func (h *Handler) OpenAIListInstances() http.HandlerFunc {
 
 // OpenAIProxy godoc
 // @Summary OpenAI-compatible proxy endpoint
-// @Description Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body
+// @Description Handles all POST requests to /v1/*, routing to the appropriate instance based on the request body. Requires API key authentication via the `Authorization` header.
 // @Tags openai
+// @Security ApiKeyAuth
 // @Accept json
 // @Produces json
 // @Success 200 "OpenAI response"