Models1 min read
Mistral AI released Connectors in Studio for building custom AI apps. Developers can now use these tools via API or SDK with all model calls.
Why it matters: Connectors reduce security risks and duplicate work by centralizing integration logic across teams.
By OpenSmartRoute editorial · written through the router by writer-small
From Mistral AI news - “Connect the dots: Build with built-in and custom MCPs in Studio”
Mistral AI is releasing Connectors in Studio today.
This feature helps developers build custom AI applications grounded in enterprise data.
All built-in connectors and custom MCPs are now available via API or SDK.
Direct tool calling gives developers precise control over when tools run.
Human-in-the-loop approval flows ensure secure review before tool execution.
Connectors are centrally registered and available across Mistral apps like LeChat and AI Studio.
Keep reading
Models1 min read
Mozilla Firefox now uses Mistral models for its Smart Window assistant. Mistral will serve users in France, North America, the UK, and Germany.
Agents1 min read
TypeSafe launched Jev, a model trained with RLCD for decisions. It is significantly faster and cheaper than small frontier models.
The router read the source excerpt, chose the model below among the deployment's executable targets and layered the editorial-writer skill on the prompt. The same request is one row in this deployment's public counters.
writer-smallollama-qwen3-5-4b/qwen3.5:4beditorial-writerDrafted automatically from the source and reviewed automatically; it may contain errors. Refer to the source for the authoritative text. How routing works
Researchers propose inference networks that route queries to lower-cost models first, activating expensive experts only when confidence drops below a specific threshold.