Mistral.ai Client

If you want to add an Mistral.ai client, go to Settings → Connections → Clients, click Add client and pick MistralAI from the client type menu.

Click Save in the toolbar to add the client.

Mistral.ai API Key

The client should appear in the clients list. If you haven't setup Mistral.ai before, you will see a warning that the API key is missing.

Click the SET API KEY button. This will open the application settings on the API Keys page where you can add your Mistral.ai API key.

For additional instructions on obtaining and setting your Mistral.ai API key, see Mistral.ai API instructions.

Click Save and after a moment the client should have a green dot next to it, indicating that it is ready to go.

Ready to use

Settings

Client Name

A unique name for the client that makes sense to you.

Model

Which model to use. Currently defaults to mistral-large-4.

Talemate lags behind Mistral.ai

When Mistral.ai adds a new model, it may take a Talemate update to add it to the list of available models. However, you can always manually enter any model name in the model field if you know the exact model identifier.

Context Length

Maximum context length (in tokens) for generations sent to Mistral.ai. If you are not sure, leave the default value.

Concurrent Inference

Found in the Concurrency section of the client editor. When enabled, batch operations that need several queries (currently visual prompt generation for image generation) can send multiple requests to the Mistral.ai API in parallel instead of one at a time, which can speed those operations up.

This is on by default. Whether concurrent requests actually complete in parallel depends on your Mistral.ai account's rate limits. See the Concurrent Requests page for more detail.

Reasoning Effort

Open the client's Reasoning section to adjust these settings:

• Reasoning Effort controls how much effort the model spends thinking. With Reasoning on, Talemate sends your choice as reasoning_effort, but only for models known to accept it: mistral-small-latest, mistral-medium-latest, mistral-large-4 and magistral-medium-latest (checked against Mistral's API). The offered levels are default, none and high: default sends nothing, so the model uses its own default, and high asks for maximum thinking. For any other model, such as mistral-large-latest, Talemate never sends an effort: the client card shows the Extra Completion Tokens field instead of the effort dropdown, and the Reasoning Effort field in the editor has no effect. If the model does not accept the selected setting, its server error is shown; choose default to omit it.
• Extra Completion Tokens adds room to the total completion limit for thinking and the answer when you enable Reasoning. It is not a separate reasoning budget.
• Thinking arrives separately from the answer, so no reasoning strip pattern is needed.

With Reasoning off, Talemate sends no effort setting at all. While Reasoning is on, the client card shows the selected effort in a dropdown next to the context token budget for the models that accept an effort; other models show the Extra Completion Tokens field.

Response Length Enforcement

Controls whether token limits and/or human-readable response length instructions are sent with prompts. Defaults to Limit tokens and send instructions.

See Response Length Enforcement for details.