AI & Models · Integration
Mistral AI
Add Mistral AI to your product for your customers, and give your AI agents governed access to it.
Mistral publishes open-weight and commercial models behind one API, which makes the interesting decision a routing decision rather than an integration decision: the same request shape reaches a small fast model or a large one, and the cost difference between them is what a product actually manages. Requests are stateless, so there is nothing to sync and nothing to store on Mistral's side, and the objects worth surfacing are the model list, the request and its output. Keys are per account, so letting each customer bring their own means their usage sits on their bill and their rate limits rather than pooling into yours. fastn holds those keys per tenant and audits every call.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer bring their own Mistral key so inference runs on their account, their quota and their bill.
Call chat completions from your product without embedding a vendor SDK per customer.
Generate embeddings for a customer's own content, with the key scoped to them.
List available models so a customer picks the cost and latency profile they want.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent calls a Mistral model as a tool within governed permissions, with each call audited.
An agent selects a smaller model for a routine step and reports the cost difference.
An agent embeds a document set on a customer's own key rather than a shared one.
Example prompt
Summarise this document set using the cheapest Mistral model that can handle the context.
Set up Mistral AI in 4 steps
- 01Enable the Mistral AI connector from your fastn dashboard.
- 02Have each customer authorise their own Mistral AI account, so calls run under their credentials rather than a shared key.
- 03Decide which models, requests and outputs your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Mistral AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Mistral AI integration without building it. Your customers connect their own Mistral AI account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Mistral AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Mistral AI connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
OpenAI
Anthropic Claude
OpenRouterOften used alongside
Tools the same teams tend to run next to Mistral AI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeMistral AI integration FAQ
How do I add a Mistral AI integration to my product?
Enable the Mistral AI connector in your fastn dashboard, then let each customer authenticate their own Mistral AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Mistral AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Mistral AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Mistral AI account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Mistral AI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent calls a Mistral model as a tool within governed permissions, with each call audited.
Who maintains the Mistral AI integration?
fastn does. When Mistral AI changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose Mistral AI API key and quota does each call use?
Each customer authorises their own Mistral AI account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Mistral AI integration?
A common starting point: let a customer bring their own Mistral key so inference runs on their account, their quota and their bill. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Mistral AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Mistral AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Mistral AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.