At a glance
- Availability: Experimental (how to enable).
- Auth: API key.
- Connection: The key comes from
MISTRAL_API_KEY. - Docs: https://docs.mistral.ai/api/
Credentials
Set these per environment. See Connect an integration.| Variable | Required | Description |
|---|---|---|
MISTRAL_API_KEY | Yes | Mistral AI API key from the La Plateforme console Docs. |
Setup
- Create a Mistral account: Go to https://console.mistral.ai and sign up or sign in to La Plateforme. Activate a workspace and add billing under Billing, or use the free Experiment tier where available.
- Create an API key: Open https://console.mistral.ai/api-keys, click ‘Create new key’, and give it a descriptive name (e.g. ‘Veryfront Integration’).
- Store the key: Copy the key immediately - it is only shown once. Add it to your .env file as MISTRAL_API_KEY=…
- Verify access: Run the List Models tool to confirm the key works. A 401 means the key is invalid or the workspace is not activated.
- API usage is billed per token - chat completion and embedding tools cost money on paid tiers
- Keys are workspace-scoped; rotate them from the console at any time
Tools
| Tool | Access | Description |
|---|---|---|
| List Models | Read | List the Mistral models available to the API key |
| Get Model | Read | Get details about a specific Mistral model |
| Create Chat Completion | Write | Generate a chat completion from a list of messages |
| Create Embedding | Write | Create embedding vectors for input text |
Example prompts
- List the Mistral models available to my API key and summarize what each is best for.
- Use Mistral to generate a chat completion for a prompt I provide.