diff --git a/Makefile b/Makefile
index a319a92935..bafd9bc4e1 100644
--- a/Makefile
+++ b/Makefile
@@ -6,7 +6,7 @@ BACKEND_PORT = 3000
 BACKEND_HOST = "127.0.0.1:$(BACKEND_PORT)"
 FRONTEND_PORT = 3001
 DEFAULT_WORKSPACE_DIR = "./workspace"
-DEFAULT_MODEL = "gpt-4-0125-preview"
+DEFAULT_MODEL = "gpt-3.5-turbo-1106"
 CONFIG_FILE = config.toml
 PRECOMMIT_CONFIG_PATH = "./dev_config/python/.pre-commit-config.yaml"
 
diff --git a/evaluation/regression/README.md b/evaluation/regression/README.md
index 67484a70b3..5a3945f2e5 100644
--- a/evaluation/regression/README.md
+++ b/evaluation/regression/README.md
@@ -14,9 +14,9 @@ To run the tests for OpenDevin project, you can use the provided test runner scr
 3. Navigate to the root directory of the project.
 4. Run the test suite using the test runner script with the required arguments:
    ```
-   python evaluation/regression/run_tests.py --OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxx --model=gpt-4-0125-preview
+   python evaluation/regression/run_tests.py --OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxx --model=gpt-3.5-turbo-1106
    ```
-   Replace `sk-xxxxxxxxxxxxxxxxxxxxxx` with your actual OpenAI API key. The default model is `gpt-4-0125-preview`, but you can specify a different model if needed.
+   Replace `sk-xxxxxxxxxxxxxxxxxxxxxx` with your actual OpenAI API key. The default model is `gpt-3.5-turbo-1106`, but you can specify a different model if needed.
 
 The test runner will discover and execute all the test cases in the `cases/` directory, and display the results of the test suite, including the status of each individual test case and the overall summary.
 
@@ -76,4 +76,4 @@ The test cases can be customized by modifying the fixtures defined in the `conft
 
 You can modify these fixtures to change the behavior of the test cases or add new ones as needed.
 
-If you have any questions or need further assistance, feel free to reach out to the project maintainers.
\ No newline at end of file
+If you have any questions or need further assistance, feel free to reach out to the project maintainers.
diff --git a/evaluation/regression/conftest.py b/evaluation/regression/conftest.py
index f784bee1c6..3267267b8d 100644
--- a/evaluation/regression/conftest.py
+++ b/evaluation/regression/conftest.py
@@ -67,9 +67,9 @@ def model(request):
         request: The pytest request object.
 
     Returns:
-        The model name, defaulting to "gpt-4-0125-preview".
-    """
-    return request.config.getoption("model", default="gpt-4-0125-preview")
+        The model name, defaulting to "gpt-3.5-turbo-1106".
+    ""
+    return request.config.getoption("model", default="gpt-3.5-turbo-1106")
 
 @pytest.fixture
 def run_test_case(test_cases_dir, workspace_dir, request):
@@ -115,7 +115,7 @@ def run_test_case(test_cases_dir, workspace_dir, request):
             "monologue_agent":"MonologueAgent",
             "codeact_agent":"CodeActAgent"
         }
-        process = subprocess.Popen(["python3", f"{SCRIPT_DIR}/../../opendevin/main.py", "-d", f"{os.path.join(agent_dir, 'workspace')}", "-c", f"{agents_ref[agent]}", "-t", f"{task}", "-m", "gpt-4-0125-preview"], stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
+        process = subprocess.Popen(["python3", f"{SCRIPT_DIR}/../../opendevin/main.py", "-d", f"{os.path.join(agent_dir, 'workspace')}", "-c", f"{agents_ref[agent]}", "-t", f"{task}", "-m", "gpt-3.5-turbo-1106"], stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
         stdout, stderr = process.communicate()
         logging.info(f"Stdout: {stdout}")
         logging.error(f"Stderr: {stderr}")
@@ -139,4 +139,4 @@ def pytest_configure(config):
             logging.FileHandler(f"test_results_{now.strftime('%Y%m%d_%H%M%S')}.log"),
             logging.StreamHandler()
         ]
-    )
\ No newline at end of file
+    )
diff --git a/opendevin/config.py b/opendevin/config.py
index b21f57cb18..643ef607d3 100644
--- a/opendevin/config.py
+++ b/opendevin/config.py
@@ -9,7 +9,7 @@ DEFAULT_CONFIG = {
     'LLM_API_KEY': None,
     'LLM_BASE_URL': None,
     'WORKSPACE_DIR': os.path.join(os.getcwd(), 'workspace'),
-    'LLM_MODEL': 'gpt-4-0125-preview',
+    'LLM_MODEL': 'gpt-3.5-turbo-1106',
     'SANDBOX_CONTAINER_IMAGE': 'ghcr.io/opendevin/sandbox',
     'RUN_AS_DEVIN': 'false',
     'LLM_EMBEDDING_MODEL': 'local',
diff --git a/opendevin/main.py b/opendevin/main.py
index 09ffde03aa..a548d32331 100644
--- a/opendevin/main.py
+++ b/opendevin/main.py
@@ -50,7 +50,7 @@ def parse_arguments():
     parser.add_argument(
         "-m",
         "--model-name",
-        default=config.get_or_default("LLM_MODEL", "gpt-4-0125-preview"),
+        default=config.get_or_default("LLM_MODEL", "gpt-3.5-turbo-1106"),
         type=str,
         help="The (litellm) model name to use",
     )
diff --git a/opendevin/server/README.md b/opendevin/server/README.md
index 45a701c736..976143c58c 100644
--- a/opendevin/server/README.md
+++ b/opendevin/server/README.md
@@ -37,7 +37,7 @@ websocat ws://127.0.0.1:3000/ws
 
 ```sh
 LLM_API_KEY=sk-... # Your OpenAI API Key
-LLM_MODEL=gpt-4-0125-preview # Default model for the agent to use
+LLM_MODEL=gpt-3.5-turbo-1106 # Default model for the agent to use
 WORKSPACE_DIR=/path/to/your/workspace # Default path to model's workspace
 ```