Use Mistral AI
Connect Maid to Mistral AI's cloud API and access Mistral Large, Mistral Small, Codestral, and other models from the European AI lab known for efficient, high-quality open-weight models.
Overview
Mistral AI is a French AI lab that has produced several notable models, including Mistral Large (a frontier-class model), Mistral Small(fast and cost-efficient), and Codestral (specialized for code generation). All are available via the Mistral cloud API using your own API key.
The Mistral provider in Maid also supports a custom base URL, which means it can connect to any self-hosted Mistral-compatible inference server — for example, a vLLM or TGI instance running a Mistral model.
Note: the Mistral provider does not support custom HTTP headers. If you need header-based authentication, consider using the OpenAI-compatible provider with a Mistral-compatible base URL instead.
Get a Mistral API key
1
Create an account at console.mistral.ai.
2
Navigate to API Keys in the left-hand menu.
3
Click Create new key and copy the generated key.
Configure Maid
1
Open Settings in Maid and select Mistral from the API dropdown.
2
Paste your API key into the API Key field.
3
Maid automatically fetches the available models. Select one from the Model dropdown — mistral-small-latest is a good cost-effective default; use mistral-large-latest for more demanding tasks.
4
Optionally set a Custom Base URL if connecting to a self-hosted Mistral-compatible server. The default is https://api.mistral.ai.
Available models
| Model | Best for |
|---|---|
| mistral-large-latest | Demanding tasks, complex reasoning |
| mistral-small-latest | Fast, cost-efficient general use |
| codestral-latest | Code generation and completion |
Configuration reference
| Field | Required | Default |
|---|---|---|
| API Key | Yes | — |
| Model | Yes | Auto-populated |
| Base URL | No | https://api.mistral.ai |
| Parameters | No | Provider defaults |