Mistral: Ministral 3 14B 2512

Ministral 3 14B 2512 is a text-and-image input model from Mistral AI with a 262,144-token context window and support for tool use. It does not support reasoning modes, and structured output support is unconfirmed. The context window is notably large, making it capable of handling long documents or extended conversations in a single pass. At $0.20 per million tokens for both input and output, the pricing is competitive for a multimodal model with tool-calling support. The key caveat is that no independent benchmark coverage exists yet, so there is no public performance data to validate real-world quality. Buyers comfortable evaluating a model through their own testing may find the price-to-context ratio worth exploring, but those who rely on third-party benchmarks before committing should wait until coverage improves.