Decision model for fixed-choice questions with calibrated probabilities in 27 European languages
Stage
Not given
Not given
Founded
Not given
Not given
Based in
HK
NO
Pricing model
Paid
Paid
Pricing
Usage-based billing with prepaid balance; selected models available at launch discounts up to 91%. Example prices: GPT-6 Astra $0.9 input / $4.5 output per 1M tokens (−91%), Claude Opus 5 $1.4 input / $7 output per 1M tokens (−72%), Gemini 3.1 Pro Preview $0.8 input / $4.8 output per 1M tokens (−60%
Zuse 27B: $0.75 per 1M input tokens (about $0.75 per 1,000 one-page decisions). Zuse 9B: $0.12 per 1M input tokens (about $0.12 per 1,000 one-page decisions). Dedicated or on-premises: Custom pricing.
Key features
One API key for LLM, image, video and music models
OpenAI-compatible API endpoints
Anthropic-native and Gemini-native protocols
Claude Code, Cursor and Cline integration
Asynchronous image, video and music generation
Unified usage dashboard and request logging
Launch discounts up to 91% on selected models
No monthly subscription, prepaid balance only
Access to 15 AI providers and 57+ models
Multi-region automatic failover
Reads documents and answers fixed-choice questions
Calibrated probability scores for each answer option
Support for 27 European languages and 115+ total languages
No output token costs
EU data hosting
65,536 tokens per document
0.2 second typical response time
87.5% accuracy on unseen tasks
What makes it different
One API key and prepaid balance for multiple providers and modalities
Transparent pricing with launch discounts up to 91% vs official prices
Same model guarantee without silent replacement or quantizing
Built-in support for coding agents and agent frameworks
Unified usage tracking and audit trail across all models and modalities