Mistral
mistralYAML config
providers:
- id: mistral:mistral-small-latest
config:
apiKey: ${MISTRAL_API_KEY}TypeScript usage
import { createProvider } from "@evalguard/core";
const provider = createProvider("mistral", process.env.MISTRAL_API_KEY);
const response = await provider.complete({
model: "mistral-small-latest",
messages: [{ role: "user", content: "Hello" }],
});Authentication
Set MISTRAL_API_KEY in your environment. EvalGuard validates the key on first call and surfaces typed errors for 401 / 403 / rate-limit responses (with Retry-After parsing).
Setup walkthrough
- 1. Sign up for an account on the Mistral website.
- 2. Obtain your API key from the account dashboard.
- 3. Review the API documentation for integration guidelines.
- 4. Set up your development environment with the necessary libraries.
- 5. Make a test API call to ensure your setup is correct.
Gotchas
- Mistral's API has a rate limit of 60 requests per minute, which can be restrictive for high-throughput applications.
- Certain models may not be available in all regions, so check the availability based on your deployment location.
- The API key must be included in every request header; failing to do so will result in authentication errors.
Cost note
Pricing starts at $0.01 per 1,000 tokens for the cheapest model and $0.06 per 1,000 tokens for the flagship model (Mistral 7B).
Recommended models
- Eval / judge
- Mistral 7B - This model offers a good balance of performance and cost for evaluation tasks.
- Agent / tool-use
- Mistral 7B - Ideal for agent-based applications due to its versatility and efficiency.
- Code
- Mistral Code - Specifically designed for code generation and understanding tasks.
- Vision
- Mistral Vision - Tailored for image processing and analysis tasks.
LLM-generated (llm-gpt-4o) · 2026-05-23