Codestral 25.01 brings low-latency code completion to more environments
Mistral released Codestral 25.01 through its API and IDE partners, with a 256,000-token context window, fill-in-the-middle support and options for deployment inside an enterprise VPC or on premises.
Why it matters: Coding models were becoming high-frequency infrastructure for inline completion and repository work, not merely assistants used in a separate chat window.