diff --git a/docs/docs/providers/inference/remote_nvidia.mdx b/docs/docs/providers/inference/remote_nvidia.mdx
index b4e04176c..657dcf3bc 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 |  | Authentication credential for the provider |
+| `api_key` | `pydantic.types.SecretStr \| None` | No |  | The NVIDIA API key, only needed of using the hosted service |
 | `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/llama_stack/providers/remote/inference/cerebras/cerebras.py b/llama_stack/providers/remote/inference/cerebras/cerebras.py
index 291336f86..21a9aa04c 100644
--- a/llama_stack/providers/remote/inference/cerebras/cerebras.py
+++ b/llama_stack/providers/remote/inference/cerebras/cerebras.py
@@ -6,7 +6,10 @@
 
 from urllib.parse import urljoin
 
-from llama_stack.apis.inference import OpenAIEmbeddingsResponse
+from llama_stack.apis.inference import (
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import CerebrasImplConfig
@@ -18,17 +21,15 @@ class CerebrasInferenceAdapter(OpenAIMixin):
     provider_data_api_key_field: str = "cerebras_api_key"
 
     def get_api_key(self) -> str:
-        return self.config.api_key.get_secret_value()
+        if self.config.auth_credential is None:
+            raise ValueError("Cerebras API key is required")
+        return self.config.auth_credential.get_secret_value()
 
     def get_base_url(self) -> str:
         return urljoin(self.config.base_url, "v1")
 
     async def openai_embeddings(
         self,
-        model: str,
-        input: str | list[str],
-        encoding_format: str | None = "float",
-        dimensions: int | None = None,
-        user: str | None = None,
+        params: OpenAIEmbeddingsRequestWithExtraBody,
     ) -> OpenAIEmbeddingsResponse:
         raise NotImplementedError()
diff --git a/llama_stack/providers/remote/inference/cerebras/config.py b/llama_stack/providers/remote/inference/cerebras/config.py
index dbab60a4b..9ba773724 100644
--- a/llama_stack/providers/remote/inference/cerebras/config.py
+++ b/llama_stack/providers/remote/inference/cerebras/config.py
@@ -7,7 +7,7 @@
 import os
 from typing import Any
 
-from pydantic import BaseModel, Field, SecretStr
+from pydantic import BaseModel, Field
 
 from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
 from llama_stack.schema_utils import json_schema_type
@@ -28,10 +28,6 @@ class CerebrasImplConfig(RemoteInferenceProviderConfig):
         default=os.environ.get("CEREBRAS_BASE_URL", DEFAULT_BASE_URL),
         description="Base URL for the Cerebras API",
     )
-    api_key: SecretStr = Field(
-        default=SecretStr(os.environ.get("CEREBRAS_API_KEY")),  # type: ignore[arg-type]
-        description="Cerebras API Key",
-    )
 
     @classmethod
     def sample_run_config(cls, api_key: str = "${env.CEREBRAS_API_KEY:=}", **kwargs) -> dict[str, Any]:
diff --git a/pyproject.toml b/pyproject.toml
index 19c21d8eb..d2352a655 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -25,7 +25,6 @@ classifiers = [
 ]
 dependencies = [
     "aiohttp",
-    "databricks-sdk",
     "fastapi>=0.115.0,<1.0",                          # server
     "fire",                                           # for MCP in LLS client
     "httpx",