diff --git a/litellm/caching.py b/litellm/caching.py
index 63e2cd39a..6906a1a98 100644
--- a/litellm/caching.py
+++ b/litellm/caching.py
@@ -15,7 +15,6 @@ from openai._models import BaseModel as OpenAIObject
 from litellm._logging import verbose_logger
 from litellm.types.services import ServiceLoggerPayload, ServiceTypes
 import traceback
-import diskcache as dc
 
 
 def print_verbose(print_statement):
@@ -1919,6 +1918,7 @@ class Cache:
 
 class DiskCache(BaseCache):
     def __init__(self, cache_dir: str = ".litellm_cache"):
+        import diskcache as dc
         # if users don't provider one, use the default litellm cache
         self.disk_cache = dc.Cache(cache_dir)
 
diff --git a/poetry.lock b/poetry.lock
index 0c1b26a9a..2911806cb 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -2679,11 +2679,11 @@ docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.link
 testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy", "pytest-ruff (>=0.2.1)"]
 
 [extras]
-extra-cache = ["diskcache"]
+disk-caching = ["diskcache"]
 extra-proxy = ["azure-identity", "azure-keyvault-secrets", "google-cloud-kms", "prisma", "resend"]
 proxy = ["PyJWT", "apscheduler", "backoff", "cryptography", "fastapi", "fastapi-sso", "gunicorn", "orjson", "python-multipart", "pyyaml", "rq", "uvicorn"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0, !=3.9.7"
-content-hash = "a21a41c1f683d7cb9a07fa76ee396b7da95cebf8c82d44de92e318916436a506"
+content-hash = "aa6283846b24f5703626c2de10459254166551f469c34e75b229adafb6985eba"
diff --git a/pyproject.toml b/pyproject.toml
index 486a04f3c..ca01141d2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -66,7 +66,7 @@ extra_proxy = [
     "resend"
 ]
 
-extra_cache = [
+disk_caching = [
     "diskcache"
 ]