Deploy your managed AI infrastructure with dedicated GPUs and optimized models.
Choose from a Model Library, featuring quantized LLMs, vLMs, embeddings, and more, or deploy your own model (e.g., Hugging Face) soon. Skip the complexities of open-weight quantization and enjoy efficient inference.
Dedicated GPU infrastructure ensures consistent and predictable performance, with unlimited tokens at a fixed hourly rate. Guaranting stable inference speeds, critical for high-load, latency-sensitive applications like chatbots.
Access your AI endpoints over a private, low-latency connection within a Virtual Private Cloud. Data sovereignty is ensured—your prompts and responses remain private, stored only in Europe, and inaccessible to third parties.
Vision language model able to analyze your images and offer insights without compromising on instruction following. Another fantastic model made by Mistral AI and distributed under the Apache 2.0 license.
Llama 3.1 by Meta is the latest iteration of the open-access Llama family, for efficient deployment and development on smaller GPUs. Llama models are tailored for dynamic dialogues and creative text generation. Engineered with the latest in efficiency and scalability, it excels in complex reasoning and coding tasks. Its advanced Grouped-Query Attention mechanism ensures unparalleled processing prowess, making it the ultimate tool for chat applications and beyond.
Llama-3.1-70b-Instruct by Meta is the most powerful model in the Llama family, boasting 70 billion parameters for unmatched text generation. Ideal for advanced AI applications, it excels in multilingual dialogues, complex reasoning, and intricate coding tasks. Its Grouped-Query Attention mechanism ensures efficient processing, making it the top choice for high-end deployment.
A 12B model with a very large context window of up to 128k tokens, particularly useful for RAG applications. Built by Mistral in collaboration with NVIDIA, this model is distributed under the Apache 2.0 license.
Trained on Scaleway's Nabuchodonosor 2023, Mixtral-8x7B is a state-of-the-art, pretrained generative model known as a Sparse Mixture of Experts. It has been benchmarked to surpass the performance of the Llama 2 70B model across a variety of tests.
An advanced embedding model that translates data into vectors, capturing complex relationships for enhanced information processing. Perfect to set up your Retrieval-Augmented Generation (RAG) system.
Try the 1st European Inference product for generative AI models on the market
You are charged for usage of the GPU type you choose.
| Model | Quantization | GPU | Price | Approx. per month |
| Llama3.1-8b-instruct | BF16, FP8 | L4-1-24G | €0.93/hour | ~€679/month |
| Llama3.1-70b-instruct | FP8 | H100-1-80G | €3.40/hour | ~€2482/month |
| Llama3.1-Nemotron-70b-instruct | FP8 | H100-1-80G | €3.40/hour | ~€2482/month |
| Mistral-7b-instruct-v0.3 | BF16 | L4-1-24G | €0.93/hour | ~€679/month |
| Pixtral-12b-2409 | BF16 | H100-1-80G | €3.40/hour | ~€2482/month |
| Mistral-nemo-instruct-2407 | FP8 | H100-1-80G | €3.40/hour | ~€2482/month |
| Mixtral-8x7b-instruct-v0.1 | FP8 | H100-1-80G | €3.40/hour | ~€2482/month |
| BGE-Multilingual-Gemma2 | FP32 | L4-1-24G | €0.93/hour | ~€679/month |
| Qwen2.5-coder-32b-instruct | INT8 | H100-1-80G | €3.40/hour | ~€2482/month |
More models and conditions available on this page.
Your AI endpoints are accessible through low-latency and secure connection to your resources hosted at Scaleway, thanks to a resilient regional Private Network.
We make generative AI endpoints compatible with Scaleway's Identity and Access Management, so that your deployments are compliant with your enterprise architecture requirements.
Identify bottlenecks on your deployments, view inference requests in real time and even report your energy consumption with a fully managed observability solution.
You'll find here a comprehensive guide on getting started, including details on deployment, security, and billing.
If you need support, don't hesitate to reach out to us through the dedicated slack community #inference-beta
Scaleway’s AI services implement robust security measures to ensure customer data privacy and integrity. Our measures and policies are published on our documentation.
Scaleway lets you seamlessly transition applications already utilizing OpenAI. You can use any of the OpenAI official libraries, for example the OpenAI Python client library, to interact with your Scaleway Managed Inference deployments. Find here the APIs and parameters supported.
Managed Inference deploys AI models and creates dedicated endpoints on a secure production infrastructure.
Alternatively, Scaleway has a selection of hosted models in its datacenters, priced per million tokens consumed, available via API. Find all details on the Generative APIs page.
Tell us the good and the bad about your experience here. Thank you for your time!
