Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Mistral
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
mistral/mistral-largeHow Mistral billing works with kRouter
Mistral is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey. 4 models are routable as mistral/<model>.
Through kRouter, Mistral serves chat and code completion, image understanding (OCR / vision-to-text), embeddings, exposed on /v1/embeddings. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Mistral is a one-line model change in your client rather than a rewrite.
Mistral models & pricing
These are the model ids kRouter routes to. This provider does not publish per-token rates.
| Model | Route as |
|---|---|
| Mistral Large 3 | mistral/mistral-large-latest |
| Codestral | mistral/codestral-latest |
| Mistral Medium 3 | mistral/mistral-medium-latest |
| Mistral Embed | mistral/mistral-embed |
Mistral links
Mistral FAQ
Is Mistral free through kRouter?
Mistral is pay-per-token: you bring your own API key and are billed by Mistral at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Mistral with Claude Code or Cursor?
Connect Mistral in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as mistral/<model>.
Which Mistral models can kRouter route to?
4 models, including Mistral Large 3, Codestral, Mistral Medium 3. Every one is addressed as mistral/<model> from any client.
What happens when Mistral is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.