diff --git a/docs/my-website/docs/adding_provider/new_rerank_provider.md b/docs/my-website/docs/adding_provider/new_rerank_provider.md
index 84c363261c..628c099443 100644
--- a/docs/my-website/docs/adding_provider/new_rerank_provider.md
+++ b/docs/my-website/docs/adding_provider/new_rerank_provider.md
@@ -17,7 +17,7 @@ class YourProviderRerankConfig(BaseRerankConfig):
             # ... other supported params
         ]
 
-    def transform_rerank_request(self, model: str, optional_rerank_params: OptionalRerankParams, headers: dict) -> dict:
+    def transform_rerank_request(self, model: str, optional_rerank_params: Dict, headers: dict) -> dict:
         # Transform request to RerankRequest spec
         return rerank_request.model_dump(exclude_none=True)
 
diff --git a/docs/my-website/docs/providers/nvidia_nim.md b/docs/my-website/docs/providers/nvidia_nim.md
index 270b356c91..9dbfc80f4e 100644
--- a/docs/my-website/docs/providers/nvidia_nim.md
+++ b/docs/my-website/docs/providers/nvidia_nim.md
@@ -15,8 +15,8 @@ https://docs.api.nvidia.com/nim/reference/
 | Description | Nvidia NIM is a platform that provides a simple API for deploying and using AI models. LiteLLM supports all models from [Nvidia NIM](https://developer.nvidia.com/nim/) |
 | Provider Route on LiteLLM | `nvidia_nim/` |
 | Provider Doc | [Nvidia NIM Docs ↗](https://developer.nvidia.com/nim/) |
-| API Endpoint for Provider | https://integrate.api.nvidia.com/v1/ |
-| Supported OpenAI Endpoints | `/chat/completions`, `/completions`, `/responses`, `/embeddings` |
+| API Endpoint for Provider | https://integrate.api.nvidia.com/v1/ (chat/embeddings), https://ai.api.nvidia.com/v1/ (rerank) |
+| Supported OpenAI Endpoints | `/chat/completions`, `/completions`, `/responses`, `/embeddings`, `/rerank` |
 
 ## API Key
 ```python
diff --git a/docs/my-website/docs/providers/nvidia_nim_rerank.md b/docs/my-website/docs/providers/nvidia_nim_rerank.md
new file mode 100644
index 0000000000..7373014a96
--- /dev/null
+++ b/docs/my-website/docs/providers/nvidia_nim_rerank.md
@@ -0,0 +1,261 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Nvidia NIM - Rerank
+
+Use Nvidia NIM Rerank models through LiteLLM.
+
+| Property | Details |
+|----------|---------|
+| Description | Nvidia NIM provides high-performance reranking models for semantic search and retrieval-augmented generation (RAG) |
+| Provider Doc | [Nvidia NIM Rerank API ↗](https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_2-nv-rerankqa-1b-v2-infer) |
+| Supported Endpoint | `/rerank` |
+
+## Overview
+
+Nvidia NIM rerank models help you:
+- Reorder search results by relevance to a query
+- Improve RAG (Retrieval-Augmented Generation) accuracy
+- Filter and rank large document sets efficiently
+
+**Supported Models:**
+- All Nvidia NIM rerank models on their platform
+
+:::tip
+
+See the full list of LiteLLM supported Nvidia NIM rerank models on [Nvidia NIM](https://models.litellm.ai)
+
+:::
+
+## Usage
+
+### LiteLLM Python SDK
+
+<Tabs>
+<TabItem value="llama-1b" label="LLaMa 1B Model">
+
+```python
+import litellm
+import os
+
+os.environ['NVIDIA_NIM_API_KEY'] = "nvapi-..."
+
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+    query="What is the GPU memory bandwidth of H100 SXM?",
+    documents=[
+        "The Hopper GPU is paired with the Grace CPU using NVIDIA's ultra-fast chip-to-chip interconnect, delivering 900GB/s of bandwidth.",
+        "A100 provides up to 20X higher performance over the prior generation.",
+        "Accelerated servers with H100 deliver 3 terabytes per second (TB/s) of memory bandwidth per GPU."
+    ],
+    top_n=3,
+)
+
+print(response)
+```
+
+</TabItem>
+<TabItem value="mistral-4b" label="Mistral 4B Model">
+
+```python
+import litellm
+import os
+
+os.environ['NVIDIA_NIM_API_KEY'] = "nvapi-..."
+
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3",
+    query="What is the GPU memory bandwidth of H100 SXM?",
+    documents=[
+        "The Hopper GPU is paired with the Grace CPU using NVIDIA's ultra-fast chip-to-chip interconnect, delivering 900GB/s of bandwidth.",
+        "A100 provides up to 20X higher performance over the prior generation.",
+        "Accelerated servers with H100 deliver 3 terabytes per second (TB/s) of memory bandwidth per GPU."
+    ],
+    top_n=3,
+)
+
+print(response)
+```
+
+</TabItem>
+</Tabs>
+
+**Response:**
+```json
+{
+    "results": [
+        {
+            "index": 2,
+            "relevance_score": 6.828125,
+            "document": {
+                "text": "Accelerated servers with H100 deliver 3 terabytes per second (TB/s) of memory bandwidth per GPU."
+            }
+        },
+        {
+            "index": 0,
+            "relevance_score": -1.564453125,
+            "document": {
+                "text": "The Hopper GPU is paired with the Grace CPU using NVIDIA's ultra-fast chip-to-chip interconnect, delivering 900GB/s of bandwidth."
+            }
+        }
+    ]
+}
+```
+
+
+## Usage with LiteLLM Proxy
+
+### 1. Setup Config
+
+Add Nvidia NIM rerank models to your proxy configuration:
+
+```yaml
+model_list:
+  - model_name: nvidia-rerank
+    litellm_params:
+      model: nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2
+      api_key: os.environ/NVIDIA_NIM_API_KEY
+```
+
+### 2. Start Proxy
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+### 3. Make Rerank Requests
+
+```bash
+curl -X POST http://0.0.0.0:4000/rerank \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "nvidia-rerank",
+    "query": "What is the GPU memory bandwidth of H100?",
+    "documents": [
+      "H100 delivers 3TB/s memory bandwidth",
+      "A100 has 2TB/s memory bandwidth",
+      "V100 offers 900GB/s memory bandwidth"
+    ],
+    "top_n": 2
+  }'
+```
+
+## API Parameters
+
+### Required Parameters
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `model` | string | The Nvidia NIM rerank model name with `nvidia_nim/` prefix |
+| `query` | string | The search query to rank documents against |
+| `documents` | array | List of documents to rank (1-1000 documents) |
+
+### Optional Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `top_n` | integer | All documents | Number of top-ranked documents to return |
+
+### Nvidia-Specific Parameters
+
+**`truncate`**: Controls how text is truncated if it exceeds the model's context window
+- `"NONE"`: No truncation (request may fail if too long)
+- `"END"`: Truncate from the end of the text
+
+```python
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+    query="GPU performance",
+    documents=["High performance computing", "Fast GPU processing"],
+    top_n=2,
+    truncate="END",  # Nvidia-specific parameter
+)
+```
+
+## Authentication
+
+Set your Nvidia NIM API key:
+
+<Tabs>
+<TabItem value="env" label="Environment Variable">
+
+```bash
+export NVIDIA_NIM_API_KEY="nvapi-..."
+```
+
+</TabItem>
+<TabItem value="python" label="Python">
+
+```python
+import os
+os.environ['NVIDIA_NIM_API_KEY'] = "nvapi-..."
+
+# Or pass directly
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+    query="test",
+    documents=["doc1"],
+    api_key="nvapi-...",
+)
+```
+
+</TabItem>
+</Tabs>
+
+## API Endpoint
+
+The rerank endpoint uses a different base URL than chat/embeddings:
+
+- **Chat/Embeddings:** `https://integrate.api.nvidia.com/v1/`
+- **Rerank:** `https://ai.api.nvidia.com/v1/`
+
+LiteLLM automatically uses the correct endpoint for rerank requests.
+
+### Custom API Base URL
+
+You can override the default base URL in several ways:
+
+**Option 1: Environment Variable**
+
+```bash
+export NVIDIA_NIM_API_BASE="https://your-custom-endpoint.com"
+```
+
+**Option 2: Pass as parameter**
+
+```python
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+    query="test",
+    documents=["doc1"],
+    api_base="https://your-custom-endpoint.com",
+)
+```
+
+**Option 3: Full URL (including model path)**
+
+If you have the complete endpoint URL, you can pass it directly:
+
+```python
+response = litellm.rerank(
+    model="nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+    query="test",
+    documents=["doc1"],
+    api_base="https://your-custom-endpoint.com/v1/retrieval/nvidia/llama-3_2-nv-rerankqa-1b-v2/reranking",
+)
+```
+
+LiteLLM will detect the full URL (by checking for `/retrieval/` in the path) and use it as-is.
+
+### How do I get an API key?
+
+Get your Nvidia NIM API key from [Nvidia's website](https://developer.nvidia.com/nim/).
+
+## Related Documentation
+
+- [Nvidia NIM - Main Documentation](./nvidia_nim)
+- [Nvidia NIM Chat Completions](./nvidia_nim#sample-usage)
+- [LiteLLM Rerank Endpoint](../rerank)
+- [Nvidia NIM Official Docs ↗](https://docs.api.nvidia.com/nim/reference/)
+
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 56baf1a702..7acd92240c 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -458,7 +458,14 @@ const sidebars = {
         "providers/deepgram",
         "providers/watsonx",
         "providers/predibase",
-        "providers/nvidia_nim",
+        {
+          type: "category",
+          label: "Nvidia NIM",
+          items: [
+            "providers/nvidia_nim",
+            "providers/nvidia_nim_rerank",
+          ]
+        },
         { type: "doc", id: "providers/nscale", label: "Nscale (EU Sovereign)" },
         "providers/xai",
         "providers/moonshot",
diff --git a/litellm/__init__.py b/litellm/__init__.py
index d1f00d3f0d..43ae1750cd 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -1061,6 +1061,7 @@ from .llms.azure_ai.rerank.transformation import AzureAIRerankConfig
 from .llms.infinity.rerank.transformation import InfinityRerankConfig
 from .llms.jina_ai.rerank.transformation import JinaAIRerankConfig
 from .llms.deepinfra.rerank.transformation import DeepinfraRerankConfig
+from .llms.nvidia_nim.rerank.transformation import NvidiaNimRerankConfig
 from .llms.clarifai.chat.transformation import ClarifaiConfig
 from .llms.ai21.chat.transformation import AI21ChatConfig, AI21ChatConfig as AI21Config
 from .llms.meta_llama.chat.transformation import LlamaAPIConfig
diff --git a/litellm/llms/base_llm/rerank/transformation.py b/litellm/llms/base_llm/rerank/transformation.py
index 8701fe57bf..6e9c03dee8 100644
--- a/litellm/llms/base_llm/rerank/transformation.py
+++ b/litellm/llms/base_llm/rerank/transformation.py
@@ -3,7 +3,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 
 import httpx
 
-from litellm.types.rerank import OptionalRerankParams, RerankBilledUnits, RerankResponse
+from litellm.types.rerank import RerankBilledUnits, RerankResponse
 from litellm.types.utils import ModelInfo
 
 from ..chat.transformation import BaseLLMException
@@ -30,7 +30,7 @@ class BaseRerankConfig(ABC):
     def transform_rerank_request(
         self,
         model: str,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         headers: dict,
     ) -> dict:
         return {}
@@ -78,7 +78,7 @@ class BaseRerankConfig(ABC):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         pass
 
     def get_error_class(
diff --git a/litellm/llms/cohere/rerank/transformation.py b/litellm/llms/cohere/rerank/transformation.py
index 5371b9a4b6..6586a83f06 100644
--- a/litellm/llms/cohere/rerank/transformation.py
+++ b/litellm/llms/cohere/rerank/transformation.py
@@ -1,8 +1,8 @@
 from typing import Any, Dict, List, Optional, Union
 
 import httpx
-import litellm
 
+import litellm
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
@@ -52,20 +52,20 @@ class CohereRerankConfig(BaseRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         """
         Map Cohere rerank params
 
         No mapping required - returns all supported params
         """
-        return OptionalRerankParams(
+        return dict(OptionalRerankParams(
             query=query,
             documents=documents,
             top_n=top_n,
             rank_fields=rank_fields,
             return_documents=return_documents,
             max_chunks_per_doc=max_chunks_per_doc,
-        )
+        ))
 
     def validate_environment(
         self,
@@ -101,7 +101,7 @@ class CohereRerankConfig(BaseRerankConfig):
     def transform_rerank_request(
         self,
         model: str,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         headers: dict,
     ) -> dict:
         if "query" not in optional_rerank_params:
diff --git a/litellm/llms/cohere/rerank_v2/transformation.py b/litellm/llms/cohere/rerank_v2/transformation.py
index 74e760460d..eb551a8a94 100644
--- a/litellm/llms/cohere/rerank_v2/transformation.py
+++ b/litellm/llms/cohere/rerank_v2/transformation.py
@@ -44,25 +44,25 @@ class CohereRerankV2Config(CohereRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         """
         Map Cohere rerank params
 
         No mapping required - returns all supported params
         """
-        return OptionalRerankParams(
+        return dict(OptionalRerankParams(
             query=query,
             documents=documents,
             top_n=top_n,
             rank_fields=rank_fields,
             return_documents=return_documents,
             max_tokens_per_doc=max_tokens_per_doc,
-        )
+        ))
 
     def transform_rerank_request(
         self,
         model: str,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         headers: dict,
     ) -> dict:
         if "query" not in optional_rerank_params:
diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py
index 173bb5a2cc..ae449bbb15 100644
--- a/litellm/llms/custom_httpx/llm_http_handler.py
+++ b/litellm/llms/custom_httpx/llm_http_handler.py
@@ -65,7 +65,7 @@ from litellm.types.llms.openai import (
     ResponseInputParam,
     ResponsesAPIResponse,
 )
-from litellm.types.rerank import OptionalRerankParams, RerankResponse
+from litellm.types.rerank import RerankResponse
 from litellm.types.responses.main import DeleteResponseResult
 from litellm.types.router import GenericLiteLLMParams
 from litellm.types.utils import (
@@ -893,7 +893,7 @@ class BaseLLMHTTPHandler:
         custom_llm_provider: str,
         logging_obj: LiteLLMLoggingObj,
         provider_config: BaseRerankConfig,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         timeout: Optional[Union[float, httpx.Timeout]],
         model_response: RerankResponse,
         _is_async: bool = False,
diff --git a/litellm/llms/deepinfra/rerank/transformation.py b/litellm/llms/deepinfra/rerank/transformation.py
index 6a3244a3c8..69c7dabebd 100644
--- a/litellm/llms/deepinfra/rerank/transformation.py
+++ b/litellm/llms/deepinfra/rerank/transformation.py
@@ -2,11 +2,11 @@
 Translate between Cohere's `/rerank` format and Deepinfra's `/rerank` format. 
 """
 
-from litellm._uuid import uuid
 from typing import Any, Dict, List, Optional, Union
 
 import httpx
 
+from litellm._uuid import uuid
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.rerank.transformation import (
     BaseLLMException,
@@ -98,7 +98,7 @@ class DeepinfraRerankConfig(BaseRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         # Start with the basic parameters
         optional_rerank_params = {}
         if query:
@@ -124,7 +124,7 @@ class DeepinfraRerankConfig(BaseRerankConfig):
     def transform_rerank_request(
         self,
         model: str,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         headers: dict,
     ) -> dict:
         # Convert OptionalRerankParams to dict as expected by parent class
diff --git a/litellm/llms/hosted_vllm/rerank/transformation.py b/litellm/llms/hosted_vllm/rerank/transformation.py
index 4ed604e2c8..2faef2c4c7 100644
--- a/litellm/llms/hosted_vllm/rerank/transformation.py
+++ b/litellm/llms/hosted_vllm/rerank/transformation.py
@@ -2,27 +2,26 @@
 Transformation logic for Hosted VLLM rerank
 """
 
-from litellm._uuid import uuid
 from typing import Any, Dict, List, Optional, Union
 
+import httpx
+
+from litellm._uuid import uuid
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
+from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
+from litellm.secret_managers.main import get_secret_str
 from litellm.types.rerank import (
+    OptionalRerankParams,
     RerankBilledUnits,
+    RerankRequest,
     RerankResponse,
     RerankResponseDocument,
     RerankResponseMeta,
     RerankResponseResult,
     RerankTokens,
-    OptionalRerankParams,
-    RerankRequest,
 )
 
-import httpx
-
-from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
-from litellm.llms.base_llm.chat.transformation import BaseLLMException
-from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
-from litellm.secret_managers.main import get_secret_str
-
 
 class HostedVLLMRerankError(BaseLLMException):
     def __init__(
@@ -72,20 +71,20 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         """
         Map parameters for Hosted VLLM rerank
         """
         if max_chunks_per_doc is not None:
             raise ValueError("Hosted VLLM does not support max_chunks_per_doc")
             
-        return OptionalRerankParams(
+        return dict(OptionalRerankParams(
             query=query,
             documents=documents,
             top_n=top_n,
             rank_fields=rank_fields,
             return_documents=return_documents,
-        )
+        ))
 
     def validate_environment(
         self,
@@ -112,7 +111,7 @@ class HostedVLLMRerankConfig(BaseRerankConfig):
     def transform_rerank_request(
         self,
         model: str,
-        optional_rerank_params: OptionalRerankParams,
+        optional_rerank_params: Dict,
         headers: dict,
     ) -> dict:
         if "query" not in optional_rerank_params:
diff --git a/litellm/llms/huggingface/rerank/transformation.py b/litellm/llms/huggingface/rerank/transformation.py
index aa0f37bc6b..1454328cc1 100644
--- a/litellm/llms/huggingface/rerank/transformation.py
+++ b/litellm/llms/huggingface/rerank/transformation.py
@@ -1,11 +1,11 @@
 import os
-from litellm._uuid import uuid
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 
 import httpx
 from typing_extensions import TypedDict
 
 import litellm
+from litellm._uuid import uuid
 from litellm.llms.base_llm.chat.transformation import BaseLLMException
 from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
 from litellm.secret_managers.main import get_secret_str
@@ -95,7 +95,7 @@ class HuggingFaceRerankConfig(BaseRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         optional_rerank_params = {}
         if non_default_params is not None:
             for k, v in non_default_params.items():
diff --git a/litellm/llms/jina_ai/rerank/transformation.py b/litellm/llms/jina_ai/rerank/transformation.py
index d8569b01b8..3bd5a4847f 100644
--- a/litellm/llms/jina_ai/rerank/transformation.py
+++ b/litellm/llms/jina_ai/rerank/transformation.py
@@ -6,11 +6,11 @@ Why separate file? Make it easy to see how transformation works
 Docs - https://jina.ai/reranker
 """
 
-from litellm._uuid import uuid
 from typing import Any, Dict, List, Optional, Tuple, Union
 
 from httpx import URL, Response
 
+from litellm._uuid import uuid
 from litellm.llms.base_llm.chat.transformation import LiteLLMLoggingObj
 from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
 from litellm.types.rerank import (
@@ -45,15 +45,15 @@ class JinaAIRerankConfig(BaseRerankConfig):
         return_documents: Optional[bool] = True,
         max_chunks_per_doc: Optional[int] = None,
         max_tokens_per_doc: Optional[int] = None,
-    ) -> OptionalRerankParams:
+    ) -> Dict:
         optional_params = {}
         supported_params = self.get_supported_cohere_rerank_params(model)
         for k, v in non_default_params.items():
             if k in supported_params:
                 optional_params[k] = v
-        return OptionalRerankParams(
+        return dict(OptionalRerankParams(
             **optional_params,
-        )
+        ))
 
     def get_complete_url(self, api_base: Optional[str], model: str) -> str:
         base_path = "/v1/rerank"
@@ -67,7 +67,7 @@ class JinaAIRerankConfig(BaseRerankConfig):
         return cleaned_base
 
     def transform_rerank_request(
-        self, model: str, optional_rerank_params: OptionalRerankParams, headers: Dict
+        self, model: str, optional_rerank_params: Dict, headers: Dict
     ) -> Dict:
         return {"model": model, **optional_rerank_params}
 
diff --git a/litellm/llms/nvidia_nim/rerank/transformation.py b/litellm/llms/nvidia_nim/rerank/transformation.py
new file mode 100644
index 0000000000..cb9fd4beba
--- /dev/null
+++ b/litellm/llms/nvidia_nim/rerank/transformation.py
@@ -0,0 +1,325 @@
+from typing import Any, Dict, List, Literal, Optional, Union
+
+import httpx
+from typing_extensions import Required, TypedDict
+
+import litellm
+from litellm._uuid import uuid
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.llms.base_llm.chat.transformation import BaseLLMException
+from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
+from litellm.secret_managers.main import get_secret_str
+from litellm.types.rerank import (
+    RerankBilledUnits,
+    RerankResponse,
+    RerankResponseMeta,
+    RerankResponseResult,
+)
+
+
+class NvidiaNimQueryObject(TypedDict):
+    text: Required[str]
+
+
+class NvidiaNimPassageObject(TypedDict):
+    text: Required[str]
+
+
+class NvidiaNimRerankRequest(TypedDict, total=False):
+    model: Required[str]
+    query: Required[NvidiaNimQueryObject]
+    passages: Required[List[NvidiaNimPassageObject]]
+    truncate: Literal["NONE", "END"]
+    top_k: int
+
+
+class NvidiaNimRankingResult(TypedDict):
+    index: Required[int]
+    logit: Required[float]
+
+
+class NvidiaNimRerankResponse(TypedDict):
+    rankings: Required[List[NvidiaNimRankingResult]]
+
+
+class NvidiaNimRerankConfig(BaseRerankConfig):
+    """
+    Reference: https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_2-nv-rerankqa-1b-v2-infer
+    
+    Nvidia NIM rerank API uses a different format:
+    - query is an object with 'text' field
+    - documents are called 'passages' and have 'text' field
+    """
+    DEFAULT_NIM_RERANK_API_BASE = "https://ai.api.nvidia.com"
+
+    def __init__(self) -> None:
+        pass
+
+    def get_complete_url(self, api_base: Optional[str], model: str) -> str:
+        """
+        Construct the Nvidia NIM rerank URL.
+        
+        Format: {api_base}/v1/retrieval/{model}/reranking
+        
+        If the user provides a full URL (e.g., {api_base}/v1/retrieval/{model}/reranking),
+        it will be used as-is.
+        """
+        if not api_base:
+            api_base = self.DEFAULT_NIM_RERANK_API_BASE
+        
+        api_base = api_base.rstrip("/")
+        
+        # Check if user already provided the full URL with /retrieval/ path
+        if "/retrieval/" in api_base:
+            return api_base
+        
+        # Ensure we don't have duplicate /v1
+        if api_base.endswith("/v1"):
+            api_base = api_base[:-3]
+        
+        return f"{api_base}/v1/retrieval/{model}/reranking"
+
+    def get_supported_cohere_rerank_params(self, model: str) -> list:
+        """
+        Nvidia NIM supports these rerank parameters.
+        """
+        return [
+            "query",
+            "documents",
+            "top_n",
+        ]
+
+    def map_cohere_rerank_params(
+        self,
+        non_default_params: Optional[dict],
+        model: str,
+        drop_params: bool,
+        query: str,
+        documents: List[Union[str, Dict[str, Any]]],
+        custom_llm_provider: Optional[str] = None,
+        top_n: Optional[int] = None,
+        rank_fields: Optional[List[str]] = None,
+        return_documents: Optional[bool] = True,
+        max_chunks_per_doc: Optional[int] = None,
+        max_tokens_per_doc: Optional[int] = None,
+    ) -> Dict:
+        """
+        Map Cohere/OpenAI rerank params to Nvidia NIM format.
+        
+        Parameter mapping:
+        - top_n (Cohere) -> top_k (Nvidia)
+        
+        Nvidia NIM specific params (passed through as-is from non_default_params):
+        - truncate: How to truncate input if too long (NONE, END)
+        """
+        optional_nvidia_nim_rerank_params: Dict[str, Any] = {
+            "query": query,
+            "documents": documents,
+        }
+        
+        # Map Cohere's top_n to Nvidia's top_k
+        if top_n is not None:
+            optional_nvidia_nim_rerank_params["top_k"] = top_n
+        
+        # Pass through Nvidia-specific params from non_default_params
+        if non_default_params:
+            optional_nvidia_nim_rerank_params.update(non_default_params)
+        return dict(optional_nvidia_nim_rerank_params)
+
+    def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        api_key: Optional[str] = None,
+    ) -> dict:
+        """
+        Validate that the Nvidia NIM API key is present.
+        """
+        if api_key is None:
+            api_key = (
+                get_secret_str("NVIDIA_NIM_API_KEY")
+                or litellm.api_key
+            )
+
+        if api_key is None:
+            raise ValueError(
+                "Nvidia NIM API key is required. Please set 'NVIDIA_NIM_API_KEY' in your environment"
+            )
+
+        default_headers = {
+            "Authorization": f"Bearer {api_key}",
+            "accept": "application/json",
+            "content-type": "application/json",
+        }
+
+        # If 'Authorization' is provided in headers, it overrides the default
+        if "Authorization" in headers:
+            default_headers["Authorization"] = headers["Authorization"]
+
+        # Merge other headers, overriding any default ones except Authorization
+        return {**default_headers, **headers}
+
+    def transform_rerank_request(
+        self,
+        model: str,
+        optional_rerank_params: Dict,
+        headers: dict,
+    ) -> dict:
+        """
+        Transform request to Nvidia NIM format.
+        
+        Nvidia NIM expects:
+        - query as {text: "..."}
+        - documents as passages: [{text: "..."}, ...]
+        - Optional: truncate (NONE or END), top_k
+        
+        Note: optional_rerank_params may contain provider-specific params like 'top_k' and 'truncate'
+        that aren't in the OptionalRerankParams TypedDict but are passed through at runtime.
+        The mapping from Cohere's 'top_n' to Nvidia's 'top_k' already happened in map_cohere_rerank_params.
+        """
+        if "query" not in optional_rerank_params:
+            raise ValueError("query is required for Nvidia NIM rerank")
+        if "documents" not in optional_rerank_params:
+            raise ValueError("documents is required for Nvidia NIM rerank")
+
+        query = optional_rerank_params["query"]
+        documents = optional_rerank_params["documents"]
+        
+        # Transform query to object format
+        query_obj: NvidiaNimQueryObject = {"text": query}
+        
+        # Transform documents to passages format
+        passages: List[NvidiaNimPassageObject] = []
+        for doc in documents:
+            if isinstance(doc, str):
+                passages.append({"text": doc})
+            elif isinstance(doc, dict):
+                # If document is already a dict, check if it has 'text' field
+                if "text" in doc:
+                    passages.append({"text": doc["text"]})
+                else:
+                    # Otherwise, stringify the dict
+                    import json
+                    passages.append({"text": json.dumps(doc)})
+            else:
+                passages.append({"text": str(doc)})
+        
+        # Note: URL path uses underscores (llama-3_2) but JSON body uses periods (llama-3.2)
+        # Convert underscores back to periods for the model field in request body
+        model_for_body = model.replace("_", ".")
+        
+        # Build request using TypedDict
+        request_data: NvidiaNimRerankRequest = {
+            "model": model_for_body,
+            "query": query_obj,
+            "passages": passages,
+        }
+        
+        # Add optional top_k parameter if provided (already mapped from top_n in map_cohere_rerank_params)
+        if "top_k" in optional_rerank_params and optional_rerank_params.get("top_k") is not None:  # type: ignore
+            request_data["top_k"] = optional_rerank_params.get("top_k")  # type: ignore
+        
+        # Add Nvidia-specific truncate parameter if provided
+        # This is passed through from non_default_params, not in base OptionalRerankParams
+        if "truncate" in optional_rerank_params and optional_rerank_params.get("truncate") is not None:  # type: ignore
+            truncate_value = optional_rerank_params.get("truncate")  # type: ignore
+            if truncate_value in ["NONE", "END"]:
+                request_data["truncate"] = truncate_value  # type: ignore
+        
+        return dict(request_data)
+
+    def transform_rerank_response(
+        self,
+        model: str,
+        raw_response: httpx.Response,
+        model_response: RerankResponse,
+        logging_obj: LiteLLMLoggingObj,
+        api_key: Optional[str] = None,
+        request_data: dict = {},
+        optional_params: dict = {},
+        litellm_params: dict = {},
+    ) -> RerankResponse:
+        """
+        Transform Nvidia NIM rerank response to LiteLLM format.
+        
+        Nvidia NIM returns (NvidiaNimRerankResponse):
+        {
+            "rankings": [
+                {
+                    "index": 0,
+                    "logit": 0.123
+                }
+            ]
+        }
+        
+        LiteLLM expects (RerankResponse):
+        {
+            "results": [
+                {
+                    "index": 0,
+                    "relevance_score": 0.123,
+                    "document": {"text": "..."}  # optional
+                }
+            ]
+        }
+        """
+        try:
+            raw_response_json = raw_response.json()
+        except Exception:
+            raise BaseLLMException(
+                status_code=raw_response.status_code,
+                message=raw_response.text,
+                headers=raw_response.headers,
+            )
+
+        # Parse as NvidiaNimRerankResponse
+        nvidia_response: NvidiaNimRerankResponse = raw_response_json
+        
+        # Transform Nvidia NIM response to LiteLLM format
+        results: List[RerankResponseResult] = []
+        rankings = nvidia_response.get("rankings", [])
+        
+        # Get original documents from request if we need to include them
+        original_passages: List[NvidiaNimPassageObject] = request_data.get("passages", [])
+        
+        for ranking in rankings:
+            result_item: RerankResponseResult = {
+                "index": ranking["index"],
+                "relevance_score": ranking["logit"],
+            }
+            
+            # Include document if it was in the original request
+            index: int = ranking["index"]
+            if index < len(original_passages):
+                result_item["document"] = {"text": original_passages[index]["text"]}  # type: ignore
+            
+            results.append(result_item)
+        
+        # Construct metadata with billed_units
+        # Nvidia NIM uses "usage" field with "total_tokens"
+        usage = raw_response_json.get("usage", {})
+        total_tokens = usage.get("total_tokens", 0)
+        
+        billed_units: RerankBilledUnits = {
+            "total_tokens": total_tokens if total_tokens > 0 else len(results)
+        }
+        
+        meta: RerankResponseMeta = {
+            "billed_units": billed_units
+        }
+        
+        return RerankResponse(
+            id=raw_response_json.get("id") or str(uuid.uuid4()),
+            results=results,
+            meta=meta,
+        )
+
+    def get_error_class(
+        self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
+    ) -> BaseLLMException:
+        return BaseLLMException(
+            status_code=status_code,
+            message=error_message,
+            headers=headers,
+        )
+
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 1b8f7f7c08..521251f50c 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -18413,6 +18413,20 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
     "sagemaker/meta-textgeneration-llama-2-13b": {
         "input_cost_per_token": 0.0,
         "litellm_provider": "sagemaker",
diff --git a/litellm/rerank_api/main.py b/litellm/rerank_api/main.py
index 5b9337e852..fc45266536 100644
--- a/litellm/rerank_api/main.py
+++ b/litellm/rerank_api/main.py
@@ -12,7 +12,7 @@ from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
 from litellm.llms.together_ai.rerank.handler import TogetherAIRerank
 from litellm.rerank_api.rerank_utils import get_optional_rerank_params
 from litellm.secret_managers.main import get_secret, get_secret_str
-from litellm.types.rerank import OptionalRerankParams, RerankResponse
+from litellm.types.rerank import RerankResponse
 from litellm.types.router import *
 from litellm.utils import ProviderConfigManager, client, exception_type
 
@@ -136,7 +136,7 @@ def rerank(  # noqa: PLR0915
             )
         )
 
-        optional_rerank_params: OptionalRerankParams = get_optional_rerank_params(
+        optional_rerank_params: Dict = get_optional_rerank_params(
             rerank_provider_config=rerank_provider_config,
             model=model,
             drop_params=kwargs.get("drop_params") or litellm.drop_params or False,
@@ -173,7 +173,7 @@ def rerank(  # noqa: PLR0915
         )
 
         # Implement rerank logic here based on the custom_llm_provider
-        if _custom_llm_provider == "cohere" or _custom_llm_provider == "litellm_proxy":
+        if _custom_llm_provider == litellm.LlmProviders.COHERE or _custom_llm_provider == litellm.LlmProviders.LITELLM_PROXY:
             # Implement Cohere rerank logic
             api_key: Optional[str] = (
                 dynamic_api_key or optional_params.api_key or litellm.api_key
@@ -205,7 +205,7 @@ def rerank(  # noqa: PLR0915
                 client=client,
                 model_response=model_response,
             )
-        elif _custom_llm_provider == "azure_ai":
+        elif _custom_llm_provider == litellm.LlmProviders.AZURE_AI:
             api_base = (
                 dynamic_api_base  # for deepinfra/perplexity/anyscale/groq/friendliai we check in get_llm_provider and pass in the api base from there
                 or optional_params.api_base
@@ -226,7 +226,7 @@ def rerank(  # noqa: PLR0915
                 client=client,
                 model_response=model_response,
             )
-        elif _custom_llm_provider == "infinity":
+        elif _custom_llm_provider == litellm.LlmProviders.INFINITY:
             # Implement Infinity rerank logic
             api_key = dynamic_api_key or optional_params.api_key or litellm.api_key
 
@@ -256,7 +256,7 @@ def rerank(  # noqa: PLR0915
                 client=client,
                 model_response=model_response,
             )
-        elif _custom_llm_provider == "together_ai":
+        elif _custom_llm_provider == litellm.LlmProviders.TOGETHER_AI:
             # Implement Together AI rerank logic
             api_key = (
                 dynamic_api_key
@@ -282,7 +282,7 @@ def rerank(  # noqa: PLR0915
                 api_key=api_key,
                 _is_async=_is_async,
             )
-        elif _custom_llm_provider == "jina_ai":
+        elif _custom_llm_provider == litellm.LlmProviders.JINA_AI:
             if dynamic_api_key is None:
                 raise ValueError(
                     "Jina AI API key is required, please set 'JINA_AI_API_KEY' in your environment"
@@ -309,7 +309,35 @@ def rerank(  # noqa: PLR0915
                 client=client,
                 model_response=model_response,
             )
-        elif _custom_llm_provider == "bedrock":
+        elif _custom_llm_provider == litellm.LlmProviders.NVIDIA_NIM:
+            if dynamic_api_key is None:
+                raise ValueError(
+                    "Nvidia NIM API key is required, please set 'NVIDIA_NIM_API_KEY' in your environment"
+                )
+
+            # Note: For rerank, the base URL is different from chat/embeddings
+            # Rerank uses ai.api.nvidia.com instead of integrate.api.nvidia.com
+            api_base = (
+                optional_params.api_base
+                or get_secret("NVIDIA_NIM_API_BASE")  # type: ignore
+                or "https://ai.api.nvidia.com"  # Default for rerank
+            )
+
+            response = base_llm_http_handler.rerank(
+                model=model,
+                custom_llm_provider=_custom_llm_provider,
+                optional_rerank_params=optional_rerank_params,
+                logging_obj=litellm_logging_obj,
+                provider_config=rerank_provider_config,
+                timeout=optional_params.timeout,
+                api_key=dynamic_api_key or optional_params.api_key,
+                api_base=api_base,
+                _is_async=_is_async,
+                headers=headers or litellm.headers or {},
+                client=client,
+                model_response=model_response,
+            )
+        elif _custom_llm_provider == litellm.LlmProviders.BEDROCK:
             api_base = (
                 dynamic_api_base
                 or optional_params.api_base
@@ -331,7 +359,7 @@ def rerank(  # noqa: PLR0915
                 logging_obj=litellm_logging_obj,
                 client=client,
             )
-        elif _custom_llm_provider == "hosted_vllm":
+        elif _custom_llm_provider == litellm.LlmProviders.HOSTED_VLLM:
             # Implement Hosted VLLM rerank logic
             api_key = (
                 dynamic_api_key
@@ -365,7 +393,7 @@ def rerank(  # noqa: PLR0915
                 model_response=model_response,
             )
 
-        elif _custom_llm_provider == "deepinfra":
+        elif _custom_llm_provider == litellm.LlmProviders.DEEPINFRA:
             api_key = (
                 dynamic_api_key
                 or optional_params.api_key
diff --git a/litellm/rerank_api/rerank_utils.py b/litellm/rerank_api/rerank_utils.py
index f70ec015b6..38e599ef82 100644
--- a/litellm/rerank_api/rerank_utils.py
+++ b/litellm/rerank_api/rerank_utils.py
@@ -1,7 +1,6 @@
 from typing import Any, Dict, List, Optional, Union
 
 from litellm.llms.base_llm.rerank.transformation import BaseRerankConfig
-from litellm.types.rerank import OptionalRerankParams
 
 
 def get_optional_rerank_params(
@@ -17,7 +16,7 @@ def get_optional_rerank_params(
     max_chunks_per_doc: Optional[int] = None,
     max_tokens_per_doc: Optional[int] = None,
     non_default_params: Optional[dict] = None,
-) -> OptionalRerankParams:
+) -> Dict:
     all_non_default_params = non_default_params or {}
     if query is not None:
         all_non_default_params["query"] = query
diff --git a/litellm/utils.py b/litellm/utils.py
index ad4d2ff11b..f963e8c944 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -7208,6 +7208,8 @@ class ProviderConfigManager:
             return litellm.HuggingFaceRerankConfig()
         elif litellm.LlmProviders.DEEPINFRA == provider:
             return litellm.DeepinfraRerankConfig()
+        elif litellm.LlmProviders.NVIDIA_NIM == provider:
+            return litellm.NvidiaNimRerankConfig()
         return litellm.CohereRerankConfig()
 
     @staticmethod
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 1b8f7f7c08..521251f50c 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -18413,6 +18413,20 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
+    "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": {
+        "input_cost_per_query": 0.0,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "nvidia_nim",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0
+    },
     "sagemaker/meta-textgeneration-llama-2-13b": {
         "input_cost_per_token": 0.0,
         "litellm_provider": "sagemaker",
diff --git a/tests/llm_translation/base_rerank_unit_tests.py b/tests/llm_translation/base_rerank_unit_tests.py
index cff4a02753..ac62dbbd8b 100644
--- a/tests/llm_translation/base_rerank_unit_tests.py
+++ b/tests/llm_translation/base_rerank_unit_tests.py
@@ -83,6 +83,14 @@ class BaseLLMRerankTest(ABC):
         """Must return the custom llm provider"""
         pass
 
+    def get_expected_cost(self) -> float:
+        """
+        Override this method to set the expected cost for the rerank call.
+        Default is None, which means the test will check cost > 0.
+        Return 0.0 for free models.
+        """
+        return None
+
     @pytest.mark.asyncio()
     @pytest.mark.parametrize("sync_mode", [True, False])
     async def test_basic_rerank(self, sync_mode):
@@ -105,7 +113,18 @@ class BaseLLMRerankTest(ABC):
             assert response.results is not None
 
             assert response._hidden_params["response_cost"] is not None
-            assert response._hidden_params["response_cost"] > 0
+            
+            # Check expected cost
+            expected_cost = self.get_expected_cost()
+            if expected_cost is not None:
+                # If expected cost is specified, check exact match or >= for 0
+                if expected_cost == 0.0:
+                    assert response._hidden_params["response_cost"] >= 0
+                else:
+                    assert response._hidden_params["response_cost"] == expected_cost
+            else:
+                # Default behavior: cost should be greater than 0
+                assert response._hidden_params["response_cost"] > 0
 
             assert_response_shape(
                 response=response, custom_llm_provider=custom_llm_provider.value
diff --git a/tests/llm_translation/test_nvidia_nim.py b/tests/llm_translation/test_nvidia_nim.py
index 89513c58b0..1705871258 100644
--- a/tests/llm_translation/test_nvidia_nim.py
+++ b/tests/llm_translation/test_nvidia_nim.py
@@ -17,6 +17,8 @@ from unittest.mock import patch, MagicMock, AsyncMock
 import litellm
 from litellm import Choices, Message, ModelResponse, EmbeddingResponse, Usage
 from litellm import completion
+from base_rerank_unit_tests import BaseLLMRerankTest
+import litellm
 
 
 def test_completion_nvidia_nim():
@@ -181,3 +183,16 @@ def test_chat_completion_nvidia_nim_with_tools():
         assert request_body["tools"] == tools
         assert request_body["tool_choice"] == "auto"
         assert request_body["parallel_tool_calls"] == True
+
+class TestNvidiaNim(BaseLLMRerankTest):
+    def get_custom_llm_provider(self) -> litellm.LlmProviders:
+        return litellm.LlmProviders.NVIDIA_NIM
+
+    def get_base_rerank_call_args(self) -> dict:
+        return {
+            "model": "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2",
+        }
+    
+    def get_expected_cost(self) -> float:
+        """Nvidia NIM rerank models are free (cost = 0.0)"""
+        return 0.0
\ No newline at end of file