From 35fda2cd05b16afc09ccc3abb0663216808763ef Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Wed, 20 Sep 2023 20:47:03 -0700
Subject: [PATCH] add latency to docs

---
 docs/my-website/docs/completion/output.md | 19 ++++++++++++++++++-
 litellm/tests/test_completion.py          |  2 +-
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/docs/my-website/docs/completion/output.md b/docs/my-website/docs/completion/output.md
index 6f7f503ff3..3016cd7da7 100644
--- a/docs/my-website/docs/completion/output.md
+++ b/docs/my-website/docs/completion/output.md
@@ -1,4 +1,6 @@
-# Output Format
+# Output 
+
+## Format
 Here's the exact json output and type you can expect from all litellm `completion` calls for all models
 
 ```python 
@@ -47,4 +49,19 @@ Here's what an example response looks like
  'model': 'claude-instant-1',
  'usage': {'prompt_tokens': 18, 'completion_tokens': 23, 'total_tokens': 41}
 }
+```
+
+## Additional Attributes
+
+You can also access information like latency. 
+
+```
+import litellm
+os.environ["ANTHROPIC_API_KEY"] = "sk-litellm-5b46387675a944d2"
+
+messages=[{"role": "user", "content": "Hey!"}]
+
+response = completion(model="claude-2", messages=messages)
+
+print(response.response_ms) # 616.25
 ```
\ No newline at end of file
diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py
index a0b39b8f0e..c1c1133f6e 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -829,11 +829,11 @@ def test_completion_ai21():
         response = completion(model=model_name, messages=messages)
         # Add any assertions here to check the response
         print(response["response_ms"])
+        print(dir(response))
         print(response.response_ms)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-test_completion_ai21()
 # test config file with completion #
 # def test_completion_openai_config():
 #     try: