by NanoGPT · family mistral-medium · listed Apr 2026RTVW
Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.
Current rates USD per 1M tokens
Input$1.50
Output$7.50
Cache read$0.75
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)