Codestral-2501

Codestral-2501

Codestral 25.01 by Mistral AI is designed for code generation, supporting 80+ programming languages, and optimized for tasks like code completion and fill-in-the-middle
Mistral AI
Version: 2

Key capabilities

About this model

Codestral 25.01 is explicitly designed for code generation tasks. It helps developers write and interact with code through a shared instruction and completion API endpoint. As it masters code and can also converse in a variety of languages, it can be used to design advanced AI applications for software developers.

Key model capabilities

  • Code generation: code completion, suggestions, translation
  • Code understanding and documentation: code summarization and explanation
  • Code quality: code review, refactoring, bug fixing and test case generation
  • Code generation with fill-in-the-middle (FIM) completion: users can define the starting point of the code using a prompt, and the ending point of the code using an optional suffix and an optional stop. The Codestral model will then generate the code that fits in between, making it ideal for tasks that require a specific piece of code to be generated.

See Responsible AI for additional considerations for responsible use.

Key use cases

  • Code generation: code completion, suggestions, translation
  • Code understanding and documentation: code summarization and explanation
  • Code quality: code review, refactoring, bug fixing and test case generation
  • Code generation with fill-in-the-middle (FIM) completion: users can define the starting point of the code using a prompt, and the ending point of the code using an optional suffix and an optional stop. The Codestral model will then generate the code that fits in between, making it ideal for tasks that require a specific piece of code to be generated.

Out of scope use cases

Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Configuration options for content filtering vary when you deploy a model for production in Azure AI; learn more .

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Quick facts

Model providerMistral AI
TypeChat completion
LifecycleGenerally available (GA)
Input typetext
Output typetext
Context window256k
Token limits4096 output