La Plateforme is Mistral AI's hosted developer platform. It provides APIs for text generation and embeddings, along with tools for model customization and deployment. Teams can use the hosted service when they do not want to operate inference infrastructure themselves, while separately released open-weight models can also be self-hosted under their respective licenses.
La Plateforme exposes its models through a hosted API, so developers can call generation, embedding, and fine-tuning endpoints without managing their own inference infrastructure. Models such as Mixtral are also released under the Apache 2.0 license, giving teams the option to self-host instead of using the hosted API.
Developers can reach Mistral's models directly through the Mistral API, through cloud marketplaces like Google's Vertex AI Model Garden and AWS SageMaker JumpStart, or through third-party inference providers such as Together AI, Anyscale, Replicate, and Perplexity. This gives teams flexibility to choose the access path that fits their existing infrastructure, whether that's a direct API integration, a cloud-native deployment, or a managed third-party endpoint.
Because models like Mixtral are open-weight, teams can fine-tune or self-host them to customize behavior for a specific use case, rather than relying solely on the hosted, proprietary versions served through La Plateforme.
More terms
Glossary term
Glossary term
Collaborate with your team on reliable Generative AI features.
Want expert guidance? Book a 1:1 onboarding session from your dashboard.