Mistral AI
Open and portable generative AI for devs and businesses
5.0•41 reviews•4.1K followers
Open and portable generative AI for devs and businesses
5.0•41 reviews•4.1K followers
- We’re committed to empower the AI community with open technology. Our open models sets the bar for efficiency, and are available for free, with fully permissive license.
- Our optimized commercial models are designed for performance and are available via our flexible deployment options.
This is the 23rd launch from Mistral AI. View more
Shieldstral
Launching today
Shieldstral is a 3B open-weight multimodal guardrail from Mistral. Define safety policies in natural language at inference time. It evaluates text, images, or both from a single token output, running locally on a single 16GB GPU.
Free
Launch Team
ChatGPT by OpenAI
Claude by Anthropic
Perplexity for Mac
Flowtica Scribe
Hi everyone!
The difficult part of moderation is deciding where a product wants to draw the line.
A kids app, a cybersecurity tool, and a mental-health platform can look at the same content very differently. Shieldstral lets you express that policy as a plain-language question at inference time, rather than relying on a fixed set of categories baked into the model.
Ask “Is this image safe for minors?” or “Does this response promote physical violence?” and the same 3B checkpoint can score text, images, or both.
It runs on one 16GB GPU, and weights are available under Apache 2.0. Teams can keep the moderation layer local and change the policy without training a new model each time.