Encrypted AI models for every workflow

Text-only reasoning model with a 256k context window and adjustable reasoning effort. Well suited for coding agents and long-running tool use. Currently in preview.

The most capable model available on Privatemode. Combines advanced reasoning with support for vision. Great for any task.

Turn document images into clean text or markdown, optionally with layout coordinates for tables and forms. Currently in preview.

gpt‑oss‑120b provides advanced reasoning capabilities in combination with great performance and affordable costs.

Transcribe multilingual audio to text with Voxtral Mini 3B’s fast ASR preview, ideal for low‑latency speech input in fully private workflows.

Generate multilingual embeddings for search and RAG using Qwen3‑Embedding 4B over an OpenAI‑compatible /v1/embeddings endpoint.

Use Whisper Large-v3 for state‑of‑the‑art speech recognition and translation.