Mistral

Before you can use Mistral as an AI provider, set up an account and API key on the Mistral platform.

1. Create an account

• Go to the Mistral console.
• Sign up using an organization account rather than a personal account (recommended).
• Set up billing and activate a plan that allows API usage.

2. Create an API key

• Open API keys in the console and create a new key.
• Use a clear naming convention, for example ai-studio-production or ai-studio-development.
• Copy the key immediately: it’s only shown once.

Secure storage

• Store API keys in a secure location, such as a secrets manager or encrypted storage.
• Never hardcode API keys in source code.
• Rotate keys periodically, especially for production environments.

Within Any2Info, API keys are stored separately from connection definitions to prevent accidental exposure: see Connections.

Note

Mistral agents always authenticate through a connection of type API headers with exactly one header, holding the API key. Collection-based authentication is not supported.

3. Available models

Select the model when creating an agent.

Model	Best for
Mistral Medium	Frontier-class multimodal model optimized for agentic and coding use cases. The default.
Mistral Large	Open-weight, general-purpose multimodal model.
Mistral Small	A fast, cost-effective model combining instruction-following, reasoning, and coding.

The Reasoning effort setting (None or High) controls how much reasoning the model applies. Higher effort generally means longer requests and more tokens used. It is not available for Mistral Large.

4. Libraries (vector stores)

Mistral calls vector stores libraries. Agents can search documents in a library, and you can manage libraries and their documents from Any2Info as with other providers.

5. Logging

Logging provides insight into how Mistral is being used, and helps with debugging and compliance.

Typical logging includes request metadata, the model used, token usage, and errors and failures. It should not include full document contents (unless explicitly required) or personal/sensitive data without proper justification.

6. Usage and cost monitoring

The Mistral console provides usage metrics. Monitor:

• Token usage per model
• Cost over time
• Spikes in usage that may indicate misconfiguration

Set internal budgets or alerts where possible, use lighter models such as Mistral Small for simple analysis tasks, and review usage periodically as agents are added or modified.

Next steps

Once your Mistral account and API key are set up, create a connection in Data Studio, select Mistral as the provider, and continue to creating your first agent.