Codestral 22B
Codestral 22B is a legacy integration reference; keep it only while you identify a current replacement.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 32k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- New production launches
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Codestral
- Released
- 2024-05-29
- Context
- 32k
- Parameters
- 22B
- Architecture
- Decoder Only
- Specialization
- general
- Training
- finetuned
Cheapest of 2 routes · Mistral AI Studio
About
Codestral 22B is a large language model developed by Mistral AI, tailored specifically for code generation tasks. It excels in assisting developers by understanding and generating code in over 80 programming languages, including popular ones like Python and Java, as well as niche languages such as Swift and Fortran. Its standout features include the ability to generate code from scratch, complete functions, write tests, and a "fill-in-the-middle" capability for completing partial code. Designed with a large context window of 32k tokens, Codestral 22B effectively handles long-range code completion tasks, making it ideal for various software development stages, including refactoring and debugging. Available on Hugging Face under a non-production license for research and testing, commercial licenses can be obtained on request.
Codestral 22B is a model in the Codestral family. The structured metadata tracks a 32k-token context window. This page tracks provider routes through NVIDIA NIM and Mistral AI Studio, with the cheapest tracked route listed at $0.3 input and $0.9 output per 1M tokens. No headline benchmark score is tracked for Codestral 22B yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
Compare all 2Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Mistral AI Studio | $0.300 | $0.900 | Serverless |
| NVIDIA NIM | - | - | ProvisionedPartial |
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.