OpenRouter lists Mistral Large 4 preview with 1M context and $0.07 cached input

Mistral Large 4 is now in public preview on OpenRouter with a 1 million token context window. Cached input is priced at $0.07 per million tokens.

The model has 1 trillion parameters, with 49 billion active, is natively multimodal, and supports up to 256K output tokens. For the first two weeks, OpenRouter is discounting it by 50%, to $0.68 per million input tokens and $2.09 per million output tokens.