scaleway · RoRoJ · Nov 19, 2025
@@ -2,7 +2,7 @@
 title: How to create an Edge Services pipeline for a Load Balancer
 description: This page explains how to configure an Edge Services pipeline on your Load Balancer, enabling a caching service for faster and more efficient delivery.
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
   posted: 2024-07-24
 tags: load-balancer edge-services cdn network cache domain https
 ---

@@ -16,7 +16,7 @@ Scaleway's Generative APIs provide access to pre-configured, serverless endpoint
 - **Managed Inference**: Allows deployment of curated or custom models with chosen quantization and Instances, offering predictable throughput and enhanced security features like private network isolation and access control. Managed Inference is billed by hourly usage, whether provisioned capacity is receiving traffic or not.
 
 ### How do I get started with Generative APIs?
-To get started, explore the [Generative APIs Playground](/generative-apis/quickstart/#start-with-the-generative-apis-playground) in the Scaleway console. For application integration, refer to our [Quickstart guide](/generative-apis/quickstart/), which provides step-by-step instructions on accessing, configuring, and using a Generative APIs endpoint.
+To get started, explore the [Generative APIs Playground](/generative-apis/quickstart/#interacting-with-generative-apis-via-the-playground) in the Scaleway console. For application integration, refer to our [Quickstart guide](/generative-apis/quickstart/), which provides step-by-step instructions on accessing, configuring, and using a Generative APIs endpoint.
 
 ## Offering and availability
 

@@ -3,7 +3,7 @@ title: How to query embedding models
 description: Learn how to interact with embedding models using Scaleway's Generative APIs service.
 tags: generative-apis ai-data embedding-models embeddings-api
 dates:
-  validation: 2025-05-12
+  validation: 2025-11-19
   posted: 2024-08-28
 ---
 import Requirements from '@macros/iam/requirements.mdx'
@@ -50,7 +50,7 @@ client = OpenAI(
 
 ### Generating embeddings with bge-multilingual-gemma2
 
-You can now generate embeddings using the `bge-multilingual-gemma2` model, such as the following example:
+You can now generate embeddings using the `bge-multilingual-gemma2` model, as shown in the following example:
 
 ```python
 # Generate embeddings using the 'bge-multilingual-gemma2' model
@@ -73,5 +73,5 @@ The following parameters can be adjusted to influence the output of the embeddin
 - **`model`** (string): The specific embedding model to use, find all our [supported models](/generative-apis/reference-content/supported-models).
 
 <Message type="warning">
- If you encounter an error such as "Forbidden 403" refer to the [API documentation](/generative-apis/api-cli/understanding-errors) for troubleshooting tips.
+ If you encounter an error such as `Forbidden 403`, refer to the [API documentation](/generative-apis/api-cli/understanding-errors) for troubleshooting tips.
 </Message>
@@ -3,7 +3,7 @@ title: How to query vision models
 description: Learn how to interact with powerful vision models using Scaleway's Generative APIs service.
 tags: generative-apis ai-data vision-models chat-completions-api
 dates:
-  validation: 2025-05-12
+  validation: 2025-11-19
   posted: 2024-10-30
 ---
 import Requirements from '@macros/iam/requirements.mdx'
@@ -15,8 +15,9 @@ Scaleway's Generative APIs service allows users to interact with powerful vision
 </Message>
 
 There are several ways to interact with vision models:
-- The Scaleway [console](https://console.scaleway.com) provides a complete [playground](/generative-apis/how-to/query-vision-models/#accessing-the-playground), aiming to test models, adapt parameters, and observe how these changes affect the output in real-time.
-- The [Chat Completions API](https://www.scaleway.com/en/developers/api/generative-apis/#path-chat-completions-create-a-chat-completion).
+
+- **Scaleway console playground** The Scaleway [console](https://console.scaleway.com) provides a complete [playground](/generative-apis/quickstart/#interacting-with-generative-apis-via-the-playground) for Generative APIs. This visual interface allows you to test models, adapt query parameters, and observe how these changes affect the output in real-time.
+- **[Chat Completions API](https://www.scaleway.com/en/developers/api/generative-apis/#path-chat-completions-create-a-chat-completion)**: Use the chat completions API to query vision models programatically.
 
 <Requirements />
 

@@ -3,16 +3,17 @@ title: Generative APIs - Quickstart
 description: Get started with Scaleway Generative APIs for powerful AI-driven content generation. Follow this guide to set up, configure, and make your first API request.
 tags: generative-apis ai-data quickstart
 dates:
-  validation: 2025-05-12
+  validation: 2025-11-18
   posted: 2024-09-04
 ---
 import Requirements from '@macros/iam/requirements.mdx'
 
 
-Generative APIs offer seamless access to pre-configured, serverless endpoints of leading AI models.
-No need to configure hardware or deploy your own models.
+Scaleway Generative APIs provide programmatic access to AI models for generating new content, such as text and code. 
 
-Hosted in European data centers and priced competitively per million tokens used, these APIs enable efficient and scalable integration of AI capabilities into your applications.
+By using our pre-configured, serverless endpoints of leading AI models, you eliminate the need to configure hardware or deploy your own models.
+
+Hosted in European data centers and priced competitively per million tokens used, Generative APIs enable efficient and scalable integration of AI capabilities into your applications.
 
 <Requirements />
 
@@ -21,79 +22,122 @@ Hosted in European data centers and priced competitively per million tokens used
   - A valid [API key](/iam/how-to/create-api-keys/)
   - Python 3.7+ installed on your system
 
-## Start with the Generative APIs Playground
+## Interacting with Generative APIs via the playground
+
+The Scaleway console provides a web playground for chat-based models hosted on Generative APIs. This allows you to interact with these models via a visual interface, sending your prompt and getting an immediate text-based response.
 
-Scaleway provides a web playground for instruct-based models hosted on Generative APIs.
+### How to access the playground
+
+1. Navigate to **Generative APIs** under the **AI** section of the [Scaleway console](https://console.scaleway.com/) side menu. The list of available models displays.
 
-### Accessing the Playground
-1. Navigate to **Generative APIs** under the **AI** section of the [Scaleway console](https://console.scaleway.com/) side menu. The list of models you can query displays.
 2. Click the name of the chat model you want to try. Alternatively, click <Icon name="more" /> next to the chat model, and click **Try model** in the menu. 
 
 The web playground displays.
 
-### Using the playground
-1. Enter a prompt at the bottom of the page, or use one of the suggested prompts in the conversation area.
-2. Edit the hyperparameters listed on the right column, for example the default temperature for more or less randomness on the outputs. 
-3. Switch models at the top of the page, to observe the capabilities of chat models offered via Generative APIs. 
-4. Click **View code** to get code snippets configured according to your settings in the playground.
+### How to use the playground
 
-## Install the OpenAI Python SDK
+1. Choose a model from the dropdown list at the top of the page.
 
-To start using Generative APIs in your code, you can install the OpenAI Python SDK. Run the following command:
+2. Enter a prompt at the bottom of the page, for example `Tell me a joke`.
 
-```bash
-pip install openai
-```
+    <Message type="tip">
+    You can also click one of the suggested prompts in the conversation area, such as `Translate text`, `Rewrite email` or `Code a pong game`, to instantly send a pre-prepared prompt and get the model's response.
+    </Message>
+
+3. Edit the hyperparameters listed on the right column, for example the default temperature for more or less randomness on the model's output.
+
+4. Click the send button to send your prompt and view the model's response in the conversation area, for example `Why don’t scientists trust atoms anymore? Because they make up everything!` 
+
+    <Message type="tip">
+    You can click **View code** next to the model dropdown to get code snippets you can integrate directly into your Python, Javascript and cURL code bases when [querying a model programatically](#interacting-with-generative-apis-programatically). These snippets are configured according to the settings you have entered in the playground.
+    </Message>
+
+## Interacting with Generative APIs programatically
+
+This example shows you how to start using Generative APIs in your Python code, via the OpenAI Python SDK.
+
+### How to install the OpenAI Python SDK
 
 <Message type="tip">
   Ensure Python is installed on your local machine. If you need to install Python, download it from [python.org](https://www.python.org/downloads/).
 </Message>
 
-## Configure and set your API key and service URL
+Run the following command:
+
+```bash
+pip install openai
+```
+
+### How to configure and set your API key and service URL
 
-1. Have your [API key](/iam/how-to/create-api-keys/) ready or generate a new one from the Scaleway console.
-2. Use the following code in your Python script:
+1. Have your [Scaleway API key](/iam/how-to/create-api-keys/) ready, or generate a new one from the Scaleway console.
 
-```py
-from openai import OpenAI
+2. Add the following code to your Python script:
 
-client = OpenAI(
-    base_url="https://api.scaleway.ai/v1", # # Scaleway's Generative APIs service URL
-    api_key="<SCW_SECRET_KEY>" # Your unique API secret key from Scaleway
-)
-```
+    ```py
+    from openai import OpenAI
 
-Make sure that you replace `<SCW_SECRET_KEY>` with the API key obtained from your Scaleway account.
+    client = OpenAI(
+        base_url="https://api.scaleway.ai/v1", # # Scaleway's Generative APIs service URL
+        api_key="<SCW_SECRET_KEY>" # Your unique API secret key from Scaleway
+    )
+    ```
 
-<Message type="tip">
-  It is recommended to store your API keys securely using environment variables or [secret management tools](/secret-manager/) to prevent unauthorized access.
-</Message>
+    Make sure that you replace `<SCW_SECRET_KEY>` with the API key obtained from your Scaleway account.
 
-## Send your first API request
+    <Message type="tip">
+      We recommend storing your API keys securely using environment variables or [secret management tools](/secret-manager/) to prevent unauthorized access.
+    </Message>
 
-You are now ready to make your first API request. Below is an example of generating a description of a futuristic city:
+### How to send your first API request
 
-```py
-from openai import OpenAI
+After installing OpenAI and adding setting up the client with the base URL and API key, you are now ready to make your first API request. 
 
-# Initialize the client with your base URL and API key
-client = OpenAI(
-    base_url="https://api.scaleway.ai/v1",
-    api_key="<SCW_API_KEY>"
-)
+Below is an example for generating a description of a futuristic city.
 
-# Create a chat completion for Llama 3.1 8b instruct
-completion = client.chat.completions.create(
-    model="llama-3.1-8b-instruct",
-    messages=[{"role": "user", "content": "Describe a futuristic city with advanced technology and green energy solutions."}],
-    temperature=0.7,
-    max_tokens=100
-)
+1. Ensure your code already contains the openai import statement and creation of a configured OpenAI client as [shown above](#how-to-configure-and-set-your-api-key-and-service-url).
 
-# Output the result
-print(completion.choices[0].message.content)
-```
+2. Create a chat completion for Llama 3.1 8b instruct by adding the following to your code:
+
+    ```python
+    completion = client.chat.completions.create(
+      model="llama-3.1-8b-instruct",
+      messages=[{"role": "user", "content": "Describe a futuristic city with advanced technology and green energy solutions."}],
+      temperature=0.7,
+      max_tokens=100
+    )
+    ```
+
+3. Output the result by adding the following to your code:
+
+    ```python
+    print(completion.choices[0].message.content)
+    ```
+
+    <Message type="tip">
+    The whole code snippet should look like this:
+
+    ```python
+    from openai import OpenAI
+
+    client = OpenAI(
+        base_url="https://api.scaleway.ai/v1", # # Scaleway's Generative APIs service URL
+        api_key="<SCW_SECRET_KEY>" # Your unique API secret key from Scaleway
+    )
+
+    # Create chat completion
+    completion = client.chat.completions.create(
+      model="llama-3.1-8b-instruct",
+      messages=[{"role": "user", "content": "Describe a futuristic city with advanced technology and green energy solutions."}],
+      temperature=0.7,
+      max_tokens=100
 
+    # Output model's response
+    print(completion.choices[0].message.content)
+    )
+    ```
+    </Message>
+
 This very simple example demonstrates how the Chat API can be used to generate creative content based on your prompts.
 
 ## Going further

@@ -2,7 +2,7 @@
 title: Discovering IoT Hub Database Route Tips & Tricks
 description: This page details advanced PostgreSQL usage in IoT database route
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 tags: iot iot-hub database cli postgresql payload plsql json mysql
 ---
 import Requirements from '@macros/iam/requirements.mdx'

@@ -2,7 +2,7 @@
 title: Getting started with the IoT Hub API
 description: This page explains how to use the IoT API from the command line using curl
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 tags: iot iot-hub io-hub-api api curl mqtt jq json
 ---
 import Requirements from '@macros/iam/requirements.mdx'

@@ -2,7 +2,7 @@
 title: Getting started with the Scaleway IoT Hub CLI
 description: This page explains how to use the IoT Hub from the command line using the Scaleway CLI
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 tags: IoT Device cli iot-hub
 ---
 import Requirements from '@macros/iam/requirements.mdx'

@@ -2,7 +2,7 @@
 title: Configuring IoT Hub routes via the CLI
 description: This page explains how to configure IoT Hub routes.
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 tags: iot iot-hub mqtt cli s3cmd amazon-s3
 ---
 import Requirements from '@macros/iam/requirements.mdx'

@@ -3,7 +3,7 @@ title: Migrating from Scaleway IoT Hub API v1beta1
 description: This page shows how to migrate to the new IoT Hub API version.
 tags: iot-hub iot hub api v1beta1
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 ---
 import Requirements from '@macros/iam/requirements.mdx'
 

@@ -3,7 +3,7 @@ title: IoT Hub - Concepts
 description: This page explains all the concepts related to IoT Hub
 tags: auto-provisioning iot authentication hub hub-event last-will message-broker mqtt mtls qos tls websocket service-level
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 ---
 
 ## Auto-provisioning

@@ -3,7 +3,7 @@ title: I can't delete my Private Network due to a reserved IPAM IP
 description: Troubleshoot issues when you can't delete your Scaleway Private Network due to a reserved IP address in IPAM.
 tags: ipam reserved-ip delete
 dates:
-  validation: 2025-05-15
+  validation: 2025-11-19
   posted: 2025-05-15
 ---
 import image from './assets/scaleway-ipam-release-ip.webp'
@@ -24,7 +24,7 @@ If your Private Network has no attached resources (Instances, Elastic Metal serv
 
 You must release the reserved private IPs from IPAM in order to delete the Private Network.
 
-In the [IPAM section](https://console.scaleway.com/ipam/) of the Scaleway console, use the filters to select the region and VPC of your Private Network. If there are any private IPs reserved for the Private Network, release them.
+In the [IPAM section](https://console.scaleway.com/ipam/) of the Scaleway console, use the filters to select the region and VPC of your Private Network. If there are any private IPs reserved for the Private Network, [release them](/ipam/how-to/reserve-ip/#how-to-release-a-reserved-private-ip-address).
 
 <Lightbox image={image} alt="A screenshot of the Scaleway console highlights the three dot menu next to a reserved private IP address in IPAM, with the 'Release IP' action" />
 

@@ -3,7 +3,7 @@ title: Understanding Access Control Lists (ACLs)
 description: Discover how Access Control Lists (ACLs) work with your Load Balancer at Scaleway, and learn how to configure them for secure and efficient traffic management.
 tags: load-balancer acl acls access-control-list access control HTTP-header filter allow reject redirect HTTPS redirection HTTP
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 ---
 import Acls from '@macros/network/acls.mdx'
 

@@ -3,7 +3,7 @@ title: Setting up your Load Balancer for HTTP/2 or HTTP/3
 description: Learn how to configure HTTP/2 and HTTP/3 protocols on your Scaleway Load Balancer to improve performance, security, and user experience for your web applications.
 tags: load-balancer http-2 http-3 http2 http3 protocol frontend backend
 dates:
-  validation: 2025-05-15
+  validation: 2025-11-19
 ---
 import image from './assets/scaleway-http-2-3.webp'
 import image2 from './assets/scaleway-enable-http3.webp'

@@ -3,7 +3,7 @@ title: Creating and configuring a Load Balancer for your Kubernetes Kapsule
 description: Configure and manage a Kubernetes Load Balancer on Scaleway to efficiently distribute traffic and scale your containerized applications.
 tags: load-balancer kubernetes kapsule loadbalancer service managed-kubernetes
 dates:
-  validation: 2025-05-15
+  validation: 2025-11-19
 ---
 
 If you are using Scaleway's [managed Kubernetes solution](/kubernetes/quickstart/), you may want to create a Load Balancer in order to expose  an application running inside your cluster to the internet.

@@ -3,7 +3,7 @@ title: Setting up SSL bridging, offloading or passthrough
 description: Learn how to configure your Scaleway Load Balancer for SSL bridging, offloading, or passthrough, and discover the different modes for handling encrypted traffic with your Load Balancer.
 tags: load-balancer ssl bridging offloading termination passthrough
 dates:
-  validation: 2025-05-14
+  validation: 2025-11-19
 ---
 import image from './assets/scaleway-ssl-bridging.webp'
 import image2 from './assets/scaleway-ssl-offloading.webp'