diff --git a/docs/docs/providers/inference/remote_nvidia.mdx b/docs/docs/providers/inference/remote_nvidia.mdx
index 657dcf3bc..b4e04176c 100644
--- a/docs/docs/providers/inference/remote_nvidia.mdx
+++ b/docs/docs/providers/inference/remote_nvidia.mdx
@@ -16,7 +16,7 @@ NVIDIA inference provider for accessing NVIDIA NIM models and AI services.
 |-------|------|----------|---------|-------------|
 | `allowed_models` | `list[str \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `<class 'bool'>` | No | False | Whether to refresh models periodically from the provider |
-| `api_key` | `pydantic.types.SecretStr \| None` | No |  | The NVIDIA API key, only needed of using the hosted service |
+| `api_key` | `pydantic.types.SecretStr \| None` | No |  | Authentication credential for the provider |
 | `url` | `<class 'str'>` | No | https://integrate.api.nvidia.com | A base url for accessing the NVIDIA NIM |
 | `timeout` | `<class 'int'>` | No | 60 | Timeout for the HTTP requests |
 | `append_api_version` | `<class 'bool'>` | No | True | When set to false, the API version will not be appended to the base_url. By default, it is true. |
diff --git a/src/llama_stack/providers/remote/inference/nvidia/config.py b/src/llama_stack/providers/remote/inference/nvidia/config.py
index b67c9e7a0..3545d2b11 100644
--- a/src/llama_stack/providers/remote/inference/nvidia/config.py
+++ b/src/llama_stack/providers/remote/inference/nvidia/config.py
@@ -7,7 +7,7 @@
 import os
 from typing import Any
 
-from pydantic import BaseModel, Field, SecretStr, field_validator
+from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
 from llama_stack.schema_utils import json_schema_type
@@ -47,10 +47,6 @@ class NVIDIAConfig(RemoteInferenceProviderConfig):
         default_factory=lambda: os.getenv("NVIDIA_BASE_URL", "https://integrate.api.nvidia.com"),
         description="A base url for accessing the NVIDIA NIM",
     )
-    api_key: SecretStr | None = Field(
-        default=None,
-        description="The NVIDIA API key, only needed of using the hosted service",
-    )
     timeout: int = Field(
         default=60,
         description="Timeout for the HTTP requests",
@@ -60,22 +56,6 @@ class NVIDIAConfig(RemoteInferenceProviderConfig):
         description="When set to false, the API version will not be appended to the base_url. By default, it is true.",
     )
 
-    @field_validator("api_key", mode="before")
-    @classmethod
-    def _default_api_key_from_env(cls, value: SecretStr | str | None) -> SecretStr | None:
-        """Populate the API key from the NVIDIA_API_KEY environment variable when absent."""
-        if value is None:
-            env_value = os.getenv("NVIDIA_API_KEY")
-            return SecretStr(env_value) if env_value else None
-
-        if isinstance(value, SecretStr):
-            return value
-
-        if isinstance(value, str):
-            return SecretStr(value)
-
-        return value
-
     @classmethod
     def sample_run_config(
         cls,