Made with these models
The model this integration runs.
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
mistral-large-latest on mistral
mistral-large-latesttext-to-text
European-hosted frontier reasoning, strong at code and multilingual work.
- European-hosted inference
- Strong at code and multilingual reasoning
- Drop-in swap with any other LLM Worker provider
- Charged on Mistral-reported token usage
- Bring your own key, or run on the platform key
Mistral Large is a frontier-class model hosted in the EU, which matters if your data residency story does. It is particularly strong at code and at multilingual work, where it holds up better than models of similar price.
In a pipeline it fills the same LLM Worker slot as Claude or GPT — planning, rewriting, extraction, routing — so swapping providers is a field change, not a rebuild. Running the same prompt through two providers and comparing is a two-node graph.
Charged on the tokens Mistral reports, at its published $2/$6 per million rate.
llmreasoningcodemultilingualmistraleu-hostedeurope