Mistral OCR 4 features bounding boxes, block classification, and inline confidence scores with extracted text. It supports 170 languages, operates in a single container for self-hosted deployments, and serves as an ingestion component for enterprise search and retrieval pipelines.

Interfaze is a new model architecture that surpasses Gemini-3-Flash, Claude-Sonnet-4.6, GPT-5.4-Mini, and Grok-4.3 in accuracy across nine benchmarks in OCR, vision, speech-to-text, and structured output tasks. The model addresses inefficiencies in human performance on complex computer-level tasks, enhancing capabilities in mapping and translation.