Mistral: Codestral 2508

Mistral: Codestral 2508 is Mistral AI's advanced language model specifically engineered for coding applications. Released in late July 2025, this model excels in tasks requiring high speed and efficiency, such as fill-in-the-middle (FIM) code completion, precise code correction, and automated test generation. Its design focuses on delivering low-latency responses for developers. This powerful model supports functions, code generation, and streaming capabilities, making it versatile for various development workflows. With an impressive 256K token context window and a maximum output of 4K tokens, it can handle complex coding challenges. Pricing is competitive at $0.30 per 1M input tokens and $0.90 per 1M output tokens, making it an accessible STARTER tier option on Multi AI.