Codestral 22B
Mistral's coding model, covering more than 80 programming languages.
Overview
Codestral 22B is Mistral AI's dedicated coding model, trained on more than 80 programming languages. It handles code completion, fill-in-the-middle and code explanation, and at 22B parameters it fits on a single high-memory GPU. Its Mistral Non-Production License doesn't allow commercial use without a separate licence from Mistral.
| Weights | Open |
|---|---|
| Parameters | 22B |
| Context window | 32K tokens |
| Licence | Mistral Non-Production License |
| Commercial use | Yes |
LLM hosts that offer Codestral 22B
All hosts →| LLM host | Hosting plan | Hosting type | Pricing |
|---|---|---|---|
| Amazon AWS | Amazon EC2 | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Google Cloud | Google Kubernetes Engine (GKE) | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity |
| Google Cloud | Compute Engine | GPU cloud | From US$0.35Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure Machine Learning | Dedicated endpoint | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure Kubernetes Service (AKS) | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |
| Microsoft Azure | Azure GPU Virtual Machines | GPU cloud | From US$0.526Per GPU-hour, Reserved or committed capacity |