Encrypted AI models for every workflow
Browse chat, coding, OCR, embedding, and speech models, all served through one confidential API.
Model IDs, context limits, endpoints, and rate limits for every model are in the documentation.
Z.ai
GLM-5.3-Flash
Smaller, faster GLM with a 1M-token context window and image input. Well suited for vision tasks and for high-volume work where latency matters.
Z.ai
GLM-5.3
Text-only reasoning model with a 1M-token context window and adjustable reasoning effort. Well suited for coding agents and long-running tool use.
DeepSeek
DeepSeek-OCR-2
Turn document images into clean text or markdown, optionally with layout coordinates for tables and forms. Currently in preview.
OpenAI
gpt-oss-120b
gpt‑oss‑120b provides advanced reasoning capabilities in combination with great performance and affordable costs.
Alibaba
Qwen3 Embedding
Generate multilingual embeddings for search and RAG using Qwen3‑Embedding 4B over an OpenAI‑compatible /v1/embeddings endpoint.
Mistral
Voxtral Mini 3B
Transcribe multilingual audio to text with Voxtral Mini 3B’s fast ASR preview, ideal for low‑latency speech input in fully private workflows.
OpenAI
Whisper Large-v3
Use Whisper Large-v3 for state‑of‑the‑art speech recognition and translation.