Quickstart
Learn how to create, access, configure, and use a Generative APIs endpoint in a few steps.
View QuickstartGenerative APIs
Generative APIs enable you to deploy, manage, and scale AI models through serverless endpoints or dedicated infrastructure, hosted in European data centers.
Generative APIs QuickstartGetting Started
Concepts
Core concepts that give you a better understanding of Scaleway Generative APIs.
View ConceptsHow-tos
Check our guides about creating, managing, and using Generative APIs endpoints.
View How-tosAdditional content
Guides to help you choose a Generative APIs endpoint, understand pricing, and advanced configuration.
View additional contentGenerative APIs Developer Reference - Serverless
Learn how to manage your Serverless endpoints through the API.
Go to Generative APIs - Serverless APIGenerative APIs Developer Reference - Dedicated Deployment
Learn how to manage your Dedicated Deployment endpoints through the API.
Go to Generative APIs - Dedicated Deployment APIChangelog
Generative APIs
DeprecatedDeprecation - Serverless models
Starting 1st July, 2026, Devstral 2, Voxtral Small, Gemma 3, Pixtral and Qwen 3 Coder on Generative APIs Serverless will be Deprecated and become End of Life in accordance with our Model Lifecycle Policy. After their End of Life date, each model request (except Voxtral Small) will be routed to a model with similar pricing and capabilities.
Generative APIs
GLM 5.2 is now available on Generative APIs. As of June 2026, GLM 5.2 is the best open-weight model for agentic and coding tasks in most benchmark evaluations. It can be plugged into your favorite agentic tools or IDE.
Generative APIs
Gemma-4-26b-a4b, Qwen3.6-35b-a3b, and Mistral-medium-3.5-128b are now available on Serverless and Dedicated Deployments. All models are frontier reasoning models with strong coding and vision capabilities.
Questions?
Visit our Help Center and find the answers to your most frequent questions.
Visit Help Center