diff --git a/pages/generative-apis/how-to/query-embedding-models.mdx b/pages/generative-apis/how-to/query-embedding-models.mdx
index 9e4de04df4..cd2176b143 100644
--- a/pages/generative-apis/how-to/query-embedding-models.mdx
+++ b/pages/generative-apis/how-to/query-embedding-models.mdx
@@ -48,7 +48,7 @@ from openai import OpenAI
 # Initialize the client with your base URL and API key
 client = OpenAI(
     base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-    api_key="<SCW_API_KEY>"  # Your unique API key from Scaleway
+    api_key="<SCW_SECRET_KEY>"  # Your unique API key from Scaleway
 )
 ```
 
diff --git a/pages/generative-apis/how-to/query-language-models.mdx b/pages/generative-apis/how-to/query-language-models.mdx
index 243ebeaf2c..1b90e86cf2 100644
--- a/pages/generative-apis/how-to/query-language-models.mdx
+++ b/pages/generative-apis/how-to/query-language-models.mdx
@@ -188,7 +188,7 @@ By default, the outputs are returned to the client only after the generation pro
   
   client = OpenAI(
       base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-      api_key="<SCW_API_KEY>"  # Your Scaleway API secret key
+      api_key="<SCW_SECRET_KEY>"  # Your Scaleway API secret key
   )
   response = client.chat.completions.create(
     model="llama-3.1-8b-instruct",
@@ -212,7 +212,7 @@ By default, the outputs are returned to the client only after the generation pro
   
   client = OpenAI(
       base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-      api_key="<SCW_API_KEY>"  # Your Scaleway API secret key
+      api_key="<SCW_SECRET_KEY>"  # Your Scaleway API secret key
   )
   
   response = client.responses.create(
@@ -243,7 +243,7 @@ The service also supports asynchronous mode for any chat completion.
 
   client = AsyncOpenAI(
       base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-      api_key="<SCW_API_KEY>"  # Your unique API key from Scaleway
+      api_key="<SCW_SECRET_KEY>"  # Your unique API key from Scaleway
   )
 
   async def main():
@@ -269,7 +269,7 @@ The service also supports asynchronous mode for any chat completion.
 
   client = AsyncOpenAI(
       base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-      api_key="<SCW_API_KEY>"  # Your unique API key from Scaleway
+      api_key="<SCW_SECRET_KEY>"  # Your unique API key from Scaleway
   )
 
   async def main():
diff --git a/pages/generative-apis/how-to/query-vision-models.mdx b/pages/generative-apis/how-to/query-vision-models.mdx
index 17aaecea93..0d34b408bc 100644
--- a/pages/generative-apis/how-to/query-vision-models.mdx
+++ b/pages/generative-apis/how-to/query-vision-models.mdx
@@ -198,7 +198,7 @@ from openai import OpenAI
 
 client = OpenAI(
     base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-    api_key="<SCW_API_KEY>"  # Your unique API key from Scaleway
+    api_key="<SCW_SECRET_KEY>"  # Your unique API key from Scaleway
 )
 response = client.chat.completions.create(
   model="mistral-small-3.2-24b-instruct-2506",
@@ -229,7 +229,7 @@ from openai import AsyncOpenAI
 
 client = AsyncOpenAI(
     base_url="https://api.scaleway.ai/v1",  # Scaleway's Generative APIs service URL
-    api_key="<SCW_API_KEY>"  # Your unique API key from Scaleway
+    api_key="<SCW_SECRET_KEY>"  # Your unique API key from Scaleway
 )
 
 async def main():
diff --git a/pages/generative-apis/how-to/use-structured-outputs.mdx b/pages/generative-apis/how-to/use-structured-outputs.mdx
index b895c24f02..74b9f9c0fa 100644
--- a/pages/generative-apis/how-to/use-structured-outputs.mdx
+++ b/pages/generative-apis/how-to/use-structured-outputs.mdx
@@ -76,7 +76,7 @@ We are using the base code below to send our LLM a voice note transcript to stru
     MODEL = "llama-3.1-8b-instruct" ## or "gpt-oss-120b" for the Responses API
 
     # Set your API key
-    API_KEY = "<SCW_API_KEY>"
+    API_KEY = "<SCW_SECRET_KEY>"
 
     client = OpenAI(
         base_url="https://api.scaleway.ai/v1",
diff --git a/pages/generative-apis/reference-content/openai-compatibility.mdx b/pages/generative-apis/reference-content/openai-compatibility.mdx
index 47af6572b8..82d118d00d 100644
--- a/pages/generative-apis/reference-content/openai-compatibility.mdx
+++ b/pages/generative-apis/reference-content/openai-compatibility.mdx
@@ -96,7 +96,7 @@ https://<Deployment UUID>.ifr.fr-par.scaleway.com/v1/embeddings
 
 ```
 curl https://<Deployment UUID>.ifr.fr-par.scaleway.com/v1/embeddings \
-  -H "Authorization: Bearer $SCW_API_KEY" \
+  -H "Authorization: Bearer $SCW_SECRET_KEY" \
   -H "Content-Type: application/json" \
   -d '{
     "input": "Embeddings can represent text in a numerical format.",
@@ -145,7 +145,7 @@ https://<Deployment UUID>.ifr.fr-par.scaleway.com/v1/models
 
 ```
 curl https://<Deployment UUID>.ifr.fr-par.scaleway.com/v1/models \
-  -H "Authorization: Bearer $SCW_API_KEY" \
+  -H "Authorization: Bearer $SCW_SECRET_KEY" \
   -H "Content-Type: application/json"
 ```
 
diff --git a/tutorials/how-to-implement-rag/index.mdx b/tutorials/how-to-implement-rag/index.mdx
index a9874ee3ee..10ba62c938 100644
--- a/tutorials/how-to-implement-rag/index.mdx
+++ b/tutorials/how-to-implement-rag/index.mdx
@@ -55,7 +55,7 @@ Create a .env file and add the following variables. These will store your API ke
 
    # Scaleway API credentials
    SCW_ACCESS_KEY=your_scaleway_access_key
-   SCW_API_KEY=your_scaleway_secret_ke
+   SCW_SECRET_KEY=your_scaleway_secret_key
    SCW_REGION=your_scaleway_region
 
    # Scaleway managed database (PostgreSQL) credentials
@@ -143,7 +143,7 @@ We will use the [OpenAIEmbeddings](https://api.python.langchain.com/en/latest/em
 # rag.py
 
 embeddings = OpenAIEmbeddings(
-                openai_api_key=os.getenv("SCW_API_KEY"),
+                openai_api_key=os.getenv("SCW_SECRET_KEY"),
                 openai_api_base=os.getenv("SCW_INFERENCE_EMBEDDINGS_ENDPOINT"),
                 model="sentence-transformers/sentence-t5-xxl",
                 tiktoken_enabled=False,
@@ -371,4 +371,4 @@ Furthermore, you can continually enhance your RAG system by implementing mechani
 
 By integrating Scaleway Object Storage, Managed Database for PostgreSQL with pgvector, and LangChain’s embedding tools, you have the foundation to build a powerful RAG system that scales with your data while offering robust information retrieval capabilities. This approach equips you with the tools necessary to handle complex queries and deliver accurate, relevant results efficiently.
 
-With ongoing refinement and adaptation, your RAG system can evolve to meet the changing needs of your users, ensuring that it remains a valuable asset in your AI toolkit.
\ No newline at end of file
+With ongoing refinement and adaptation, your RAG system can evolve to meet the changing needs of your users, ensuring that it remains a valuable asset in your AI toolkit.