AI Agent · Mistral
A Mistral-powered support agent
Run your ChatFlo agent on Mistral's models. For teams with a European vendor preference — or a procurement checklist that asks about it — Mistral is a first-class choice rather than a fallback.
Can ChatFlo run my support agent on Mistral?
ChatFlo can run your support agent on Mistral Large or Mistral Small, grounded in your own documentation. No Mistral account or API key is required; usage is included in your plan. Mistral is typically chosen by teams with a European vendor preference, and performs strongly on French, Spanish, and other European-language conversations.
Why Mistral
The European option, for teams who care where the model is from.
A European model vendor
Mistral is a French company. For teams whose procurement or internal policy asks about vendor location, that answer is sometimes the deciding factor rather than a detail.
Strong on European languages
French, Spanish, Italian, and German conversations read naturally, which matters if a meaningful share of your queue is not in English.
Small model, low cost
Mistral Small is a genuinely cheap option for high-volume routine questions where the answer is short and the source is unambiguous.
Available models
The Mistral AI models you can select
Pick one in AI settings. Switching is a setting, not a migration — your training content, guardrails, and history stay where they are.
Mistral Large
Most capable
Mistral Small
Fast and cheap for high volume
When another model is the better call
On complex, multi-step English support threads, GPT-4o and Claude Sonnet 5 are generally stronger. Mistral is the right pick when vendor origin or European-language quality is what you are optimising for.
Run your agent on Mistral
Select Mistral in AI settings. Everything else about your agent stays where it is.
Frequently asked questions
Model processing location depends on the provider you select, and is a question we answer specifically rather than generally — talk to us before you commit if it is a procurement requirement, and we will confirm the current arrangement for your plan and region in writing.
Yes — the agent detects the language a customer writes in and replies in it. Mistral's particular strength is European languages; if most of your queue is in an Asian language, test Gemini or GPT-4o alongside it before you settle.
No. ChatFlo runs the model for you on every paid plan — there is no separate Mistral AI account, billing relationship, or key to manage. Model usage is included in your plan.
Yes, from the AI settings screen, at any time. The model is a setting on your agent, not a plan tier — your training content, guardrails, tone, and conversation history are untouched by the switch, so you can A/B two models on the same setup.
No. Training is the same regardless of model: you point ChatFlo at your website, docs, and files, and it indexes them. The model only affects how answers are composed from that material — it never changes what the agent is allowed to draw on.
Other models
ChatFlo is not locked to one model vendor
Your agent runs on whichever of these you select, and you can change your mind without rebuilding anything.