Use Codestral 25.01 with Continue today

When Mistral AI launched the original Codestral model in May 2024, it immediately became the best autocomplete model—a Large Language Model (LLM) trained for code infilling and capable of low latency responses. This is why it has been our top recommendation for developers since then.

And now, six months later, Codestral 25.01 represents a big step forward! With its more efficient architecture and an improved tokenizer compared to the original, it is over 2 times faster and provides even better code completion suggestions.

You can try it out with Continue yourself today. For enterprise use cases, especially ones that require data and model residency, Codestral 25.01 is available to deploy locally within your premises or virtual private cloud (VPC). You can also use it via API on Mistral’s la Plateforme, Google Cloud’s Vertex AI, and Azure AI Foundry. It will be available via API on Amazon Bedrock soon too.

Try Codestral 25.01 now in VS Code or JetBrains or get in touch with us about enterprise deployments here.