Mistral: Codestral Mamba
mistralai/codestral-mamba
Updated Jul 19256,000 context
$0.25/M input tokens$0.25/M output tokens
A 7.3B parameter Mamba-based model designed for code and reasoning tasks.
- Linear time inference, allowing for theoretically infinite sequence lengths
- 256k token context window
- Optimized for quick responses, especially beneficial for code productivity
- Performs comparably to state-of-the-art transformer models in code and reasoning tasks
- Available under the Apache 2.0 license for free use, modification, and distribution