diff --git a/tests/trace/builtin_objects/backend_models.ipynb b/tests/trace/builtin_objects/backend_models.ipynb
new file mode 100644
index 00000000000..ba835ae269d
--- /dev/null
+++ b/tests/trace/builtin_objects/backend_models.ipynb
@@ -0,0 +1,251 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"WF_TRACE_SERVER_URL\"] = \"http://127.0.01:6345\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import weave"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Logged in as Weights & Biases user: timssweeney.\n",
+      "View Weave data at https://wandb.ai/timssweeney/remote_model_demo/weave\n"
+     ]
+    }
+   ],
+   "source": [
+    "client = weave.init(\"remote_model_demo_2\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🍩 https://wandb.ai/timssweeney/remote_model_demo/r/call/0193b497-27e9-7f31-8f26-a24d76254d32\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Fred', 'age': 30}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Demonstrates creating a model in python\n",
+    "\n",
+    "from weave.builtin_objects.models.CompletionModel import LiteLLMCompletionModel\n",
+    "\n",
+    "model = LiteLLMCompletionModel(\n",
+    "    model=\"gpt-4o\",\n",
+    "    messages_template=[\n",
+    "        {\"role\": \"system\", \"content\": \"Please extract the name and age from the following text\"},\n",
+    "        {\"role\": \"user\", \"content\": \"{user_input}\"},\n",
+    "    ],\n",
+    "    response_format={\n",
+    "        \"type\": \"json_schema\",\n",
+    "        \"json_schema\": {\n",
+    "            \"name\": \"Person\",\n",
+    "            \"schema\": {\n",
+    "                \"type\": \"object\",\n",
+    "                \"properties\": {\n",
+    "                    \"age\": {\"type\": \"integer\"},\n",
+    "                    \"name\": {\"type\": \"string\"},\n",
+    "                },\n",
+    "            }\n",
+    "        }\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "res = model.predict(user_input=\"Hello, my name is Fred and I am 30 years old.\")\n",
+    "\n",
+    "print(model.ref.uri())\n",
+    "\n",
+    "print(res)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "CallMethodRes(call_id='0193b497-3c5b-7121-9a88-f14798eac933', output={'name': 'Charles', 'age': 40})"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Demonstrates calling a model created in python\n",
+    "\n",
+    "from weave.trace_server.trace_server_interface import CallMethodReq\n",
+    "\n",
+    "call_res = client.server.call_method(CallMethodReq(\n",
+    "    project_id=client._project_id(),\n",
+    "    object_ref=model.ref.uri(),\n",
+    "    method_name=\"predict\",\n",
+    "    args={\n",
+    "        \"user_input\": \"Hello, my name is Charles and I am 40 years old.\"\n",
+    "    }\n",
+    "))\n",
+    "\n",
+    "call_res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ObjCreateRes(digest='GSK0zJwYfB7Scv2StQWsxGtoxuvuGxTSEOFzKSrmkAg')"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Demonstrates creating a model in the UI - notice the digest match\n",
+    "\n",
+    "from weave.trace_server.trace_server_interface import ObjCreateReq\n",
+    "\n",
+    "obj_res = client.server.obj_create(ObjCreateReq.model_validate({'obj': {\n",
+    "    \"project_id\": client._project_id(),\n",
+    "    \"object_id\": \"LiteLLMCompletionModel\",\n",
+    "    \"val\": {\n",
+    "        \"model\": \"gpt-4o\",\n",
+    "        \"messages_template\": [{\"role\": \"user\", \"content\": \"{user_input}\"}],\n",
+    "        \"response_format\": {\n",
+    "            \"type\": \"json_schema\",\n",
+    "            \"json_schema\": {\n",
+    "                \"name\": \"Person\",\n",
+    "                \"schema\": {\n",
+    "                    \"type\": \"object\",\n",
+    "                    \"properties\": {\n",
+    "                        \"age\": {\"type\": \"integer\"},\n",
+    "                        \"name\": {\"type\": \"string\"},\n",
+    "                    },\n",
+    "                },\n",
+    "            },\n",
+    "        },\n",
+    "    },\n",
+    "    \"set_leaf_object_class\": \"LiteLLMCompletionModel\",\n",
+    "}}))\n",
+    "\n",
+    "obj_res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🍩 https://wandb.ai/timssweeney/remote_model_demo/r/call/0193b498-a593-7391-b059-b32909b46f93\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'name': 'Fred', 'age': 30}"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Demonstrates fetching a model in python that was created in the UI\n",
+    "\n",
+    "from weave.trace.refs import ObjectRef\n",
+    "\n",
+    "gotten_model = weave.ref(ObjectRef(\n",
+    "    entity=client.entity,\n",
+    "    project=client.project,\n",
+    "    name=\"LiteLLMCompletionModel\",\n",
+    "    _digest=obj_res.digest\n",
+    ").uri()).get()\n",
+    "\n",
+    "res = gotten_model.predict(user_input=\"Hello, my name is Fred and I am 30 years old.\")\n",
+    "res"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "wandb-weave",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/weave/trace_server_bindings/remote_http_trace_server.py b/weave/trace_server_bindings/remote_http_trace_server.py
index b749af60d24..2e7b9054a97 100644
--- a/weave/trace_server_bindings/remote_http_trace_server.py
+++ b/weave/trace_server_bindings/remote_http_trace_server.py
@@ -568,6 +568,11 @@ def completions_create(
             tsi.CompletionsCreateReq,
             tsi.CompletionsCreateRes,
         )
+    
+    def call_method(self, req: tsi.CallMethodReq) -> tsi.CallMethodRes:
+        return self._generic_request(
+            "/execute/method", req, tsi.CallMethodReq, tsi.CallMethodRes
+        )
 
 
 __docspec__ = [