diff --git a/docs/my-website/docs/providers/nvidia_nim.md b/docs/my-website/docs/providers/nvidia_nim.md
new file mode 100644
index 000000000..f90450768
--- /dev/null
+++ b/docs/my-website/docs/providers/nvidia_nim.md
@@ -0,0 +1,103 @@
+# Nvidia NIM
+https://docs.api.nvidia.com/nim/reference/
+
+:::tip
+
+**We support ALL Nvidia NIM models, just set `model=nvidia_nim/<any-model-on-nvidia_nim>` as a prefix when sending litellm requests**
+
+:::
+
+## API Key
+```python
+# env variable
+os.environ['NVIDIA_NIM_API_KEY']
+```
+
+## Sample Usage
+```python
+from litellm import completion
+import os
+
+os.environ['NVIDIA_NIM_API_KEY'] = ""
+response = completion(
+    model=model_name,
+    messages=[
+        {
+            "role": "user",
+            "content": "What's the weather like in Boston today in Fahrenheit?",
+        }
+    ],
+    temperature=0.2,        # optional
+    top_p=0.9,              # optional
+    frequency_penalty=0.1,  # optional
+    presence_penalty=0.1,   # optional
+    max_tokens=10,          # optional
+    stop=["\n\n"],          # optional
+)
+print(response)
+```
+
+## Sample Usage - Streaming
+```python
+from litellm import completion
+import os
+
+os.environ['NVIDIA_NIM_API_KEY'] = ""
+response = completion(
+    model=model_name,
+    messages=[
+        {
+            "role": "user",
+            "content": "What's the weather like in Boston today in Fahrenheit?",
+        }
+    ],
+    stream=True,
+    temperature=0.2,        # optional
+    top_p=0.9,              # optional
+    frequency_penalty=0.1,  # optional
+    presence_penalty=0.1,   # optional
+    max_tokens=10,          # optional
+    stop=["\n\n"],          # optional
+)
+
+for chunk in response:
+    print(chunk)
+```
+
+
+## Supported Models - 💥 ALL Nvidia NIM Models Supported!
+We support ALL `nvidia_nim` models, just set `nvidia_nim/` as a prefix when sending completion requests
+
+| Model Name | Function Call |
+|------------|---------------|
+| nvidia/nemotron-4-340b-reward | `completion(model="nvidia_nim/nvidia/nemotron-4-340b-reward", messages)` |
+| 01-ai/yi-large | `completion(model="nvidia_nim/01-ai/yi-large", messages)` |
+| aisingapore/sea-lion-7b-instruct | `completion(model="nvidia_nim/aisingapore/sea-lion-7b-instruct", messages)` |
+| databricks/dbrx-instruct | `completion(model="nvidia_nim/databricks/dbrx-instruct", messages)` |
+| google/gemma-7b | `completion(model="nvidia_nim/google/gemma-7b", messages)` |
+| google/gemma-2b | `completion(model="nvidia_nim/google/gemma-2b", messages)` |
+| google/codegemma-1.1-7b | `completion(model="nvidia_nim/google/codegemma-1.1-7b", messages)` |
+| google/codegemma-7b | `completion(model="nvidia_nim/google/codegemma-7b", messages)` |
+| google/recurrentgemma-2b | `completion(model="nvidia_nim/google/recurrentgemma-2b", messages)` |
+| ibm/granite-34b-code-instruct | `completion(model="nvidia_nim/ibm/granite-34b-code-instruct", messages)` |
+| ibm/granite-8b-code-instruct | `completion(model="nvidia_nim/ibm/granite-8b-code-instruct", messages)` |
+| mediatek/breeze-7b-instruct | `completion(model="nvidia_nim/mediatek/breeze-7b-instruct", messages)` |
+| meta/codellama-70b | `completion(model="nvidia_nim/meta/codellama-70b", messages)` |
+| meta/llama2-70b | `completion(model="nvidia_nim/meta/llama2-70b", messages)` |
+| meta/llama3-8b | `completion(model="nvidia_nim/meta/llama3-8b", messages)` |
+| meta/llama3-70b | `completion(model="nvidia_nim/meta/llama3-70b", messages)` |
+| microsoft/phi-3-medium-4k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-medium-4k-instruct", messages)` |
+| microsoft/phi-3-mini-128k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-mini-128k-instruct", messages)` |
+| microsoft/phi-3-mini-4k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-mini-4k-instruct", messages)` |
+| microsoft/phi-3-small-128k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-small-128k-instruct", messages)` |
+| microsoft/phi-3-small-8k-instruct | `completion(model="nvidia_nim/microsoft/phi-3-small-8k-instruct", messages)` |
+| mistralai/codestral-22b-instruct-v0.1 | `completion(model="nvidia_nim/mistralai/codestral-22b-instruct-v0.1", messages)` |
+| mistralai/mistral-7b-instruct | `completion(model="nvidia_nim/mistralai/mistral-7b-instruct", messages)` |
+| mistralai/mistral-7b-instruct-v0.3 | `completion(model="nvidia_nim/mistralai/mistral-7b-instruct-v0.3", messages)` |
+| mistralai/mixtral-8x7b-instruct | `completion(model="nvidia_nim/mistralai/mixtral-8x7b-instruct", messages)` |
+| mistralai/mixtral-8x22b-instruct | `completion(model="nvidia_nim/mistralai/mixtral-8x22b-instruct", messages)` |
+| mistralai/mistral-large | `completion(model="nvidia_nim/mistralai/mistral-large", messages)` |
+| nvidia/nemotron-4-340b-instruct | `completion(model="nvidia_nim/nvidia/nemotron-4-340b-instruct", messages)` |
+| seallms/seallm-7b-v2.5 | `completion(model="nvidia_nim/seallms/seallm-7b-v2.5", messages)` |
+| snowflake/arctic | `completion(model="nvidia_nim/snowflake/arctic", messages)` |
+| upstage/solar-10.7b-instruct | `completion(model="nvidia_nim/upstage/solar-10.7b-instruct", messages)` |
\ No newline at end of file
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 2673933f4..9835a260b 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -146,13 +146,14 @@ const sidebars = {
         "providers/databricks",
         "providers/watsonx",
         "providers/predibase",
-        "providers/clarifai",
+        "providers/nvidia_nim", 
         "providers/triton-inference-server",
         "providers/ollama", 
         "providers/perplexity", 
         "providers/groq", 
         "providers/deepseek", 
-        "providers/fireworks_ai", 
+        "providers/fireworks_ai",
+        "providers/clarifai", 
         "providers/vllm", 
         "providers/xinference", 
         "providers/cloudflare_workers",