Mistral AI
Overview
Protect your Mistral AI integration with LockLLM's transparent proxy layer. Route all Mistral requests through LockLLM for automatic prompt injection scanning without modifying your application logic. Compatible with Mistral 3, Mistral Large 3, and all Mistral AI model variants built on European infrastructure.
The integration maintains Mistral's complete API interface, including function calling, streaming, and JSON mode. Your existing code works exactly as before, with added security protection.
How it Works
Update your Mistral client's base URL to route through the LockLLM proxy. All requests are intercepted, prompts are scanned for security threats in real-time, and safe requests are forwarded to Mistral. Malicious prompts are blocked before reaching the model.
The proxy adds 150-250ms overhead and operates transparently. All standard Mistral features including streaming, function calling, and embeddings work without modification.
Supported Models
All Mistral AI models are supported through the proxy:
- Mistral 3 (latest generation)
- Mistral Large 3 (flagship model)
- Mistral Medium and Small
- Mistral Embed for embeddings
- All legacy Mistral 2 and Mixtral variants
Quick Start
Update your Mistral client configuration to route through the proxy:
import { MistralClient } from '@mistralai/mistralai'
const client = new MistralClient({
apiKey: process.env.MISTRAL_API_KEY,
serverURL: 'https://api.lockllm.com/v1/proxy/mistral',
defaultHeaders: {
'X-LockLLM-Key': process.env.LOCKLLM_API_KEY
}
})
// All requests are automatically scanned
const response = await client.chat({
model: 'mistral-large-3',
messages: [{ role: 'user', content: userInput }]
})Features
- Automatic Scanning: All prompts scanned without code changes
- Full Model Support: Works with all Mistral models
- Function Calling: Preserves tool use capabilities
- Streaming Support: Compatible with streaming responses
- JSON Mode: Works with structured outputs
- European Infrastructure: Compatible with EU data requirements
Getting Started
Generate API keys in the dashboard, update your client configuration with the proxy URL, and start making secure requests. Visit the documentation for complete setup guides and examples.