Quickstart
Learn how to access, configure and use a Generative APIs endpoint in a few steps.
View QuickstartGenerative APIs
Generative APIs provide access to pre-configured serverless endpoints of the most popular AI models, hosted in European data centers and priced per 1M tokens used.
Generative APIs QuickstartGetting Started
Concepts
Core concepts that give you a better understanding of Scaleway Generative APIs.
View ConceptsHow-tos
Check our guides about 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
Developer reference documentation for Scaleway Generative APIs.
Go to Generative APIsChangelog
Generative APIs
Qwen3 Embedding 8B is a state-of-the-art embedding model, ranking 3rd on the MTEB leaderboard as of November 2025. It supports custom embedding dimensions (also known as Matryoshka embeddings). Holo2 is a frontier model designed to analyze user interfaces and interact with them. Holo2 enables browser automation, as well as interaction with thick-client and mobile applications.
Generative APIs
Whisper Large v3 is now available on Generative APIs.
Both Whisper Large v3 and Voxtral Small 24B can now be queried to perform audio transcription using Audio Transcriptions API.
Generative APIs
DeprecatedDevstral small is now deprecated
Devstral small will not exit Preview stage and is now deprecated.
Following our model lifecycle policy, this model will remain accessible until November 14th, 2025. After this date, requests will be routed automatically to a similar model: Qwen3 Coder.
Questions?
Visit our Help Center and find the answers to your most frequent questions.
Visit Help Center