European-grade sovereignty. Efficient, open, and enterprise-ready.
Mistral AI offers a family of highly efficient models — from the compact Mistral 7B to the enterprise-grade Mistral Large and Magistral reasoning model. For organisations with data residency requirements in the EU, or those wanting open-weight models they can self-host, Mistral on Nagent provides the ideal sovereign AI path.
Best-in-class for EU data residency
Context Window
128K tokens
Max Output
8K tokens
Input Types
Text
Output Types
Text, Code, JSON
Advanced reasoning model
Context Window
128K tokens
Max Output
40K tokens
Input Types
Text
Output Types
Text, Code
Ultra-fast, cost-efficient
Context Window
32K tokens
Max Output
8K tokens
Input Types
Text
Output Types
Text, Code
Best-in-class code generation
Context Window
256K tokens
Max Output
32K tokens
Input Types
Text, Code
Output Types
Code
Multimodal Mistral
Context Window
128K tokens
Max Output
8K tokens
Input Types
Text, Images
Output Types
Text
Run agents on EU infrastructure with Mistral — full data sovereignty, no transatlantic data transfer.
Codestral's 256K context handles full-codebase refactors, automated PR reviews, and test generation.
Mistral Small handles millions of classification, extraction, and summarisation tasks at very low cost.
Open-weight Mistral models can be self-hosted inside your infrastructure via Nagent's sovereign AI setup.
Nagent adds enterprise orchestration, observability, and workflow automation on top of Mistral AI's raw model capabilities.
EU data residency guaranteed — no data leaves European infrastructure
Open-weight variants available for fully air-gapped self-hosted deployments
Codestral excels at developer-facing agents in CI/CD pipelines
Mistral's function-calling is natively supported in Nagent's tool framework
Navigate to Agent Studio in your Nagent workspace.
Choose Mistral and pick your model. For sovereign deployments, select the self-hosted option.
If required, enable EU-only routing in your workspace settings before deploying.
Get started in minutes — no API key management required.
