Sovereign inference — TF Mystica

Your sovereign, private TF Mystica

TF Mystica is ToothFairyAI's flagship model system: an advanced orchestration architecture that pairs a custom routing engine with a hybrid pool of frontier open-weight models and ToothFairyAI fine-tunes, purpose-built for agentic workflows. It specialises in tool calling, multi-step planning, adaptive depth and long-running agent state management — capabilities that surpass state-of-the-art closed-source models in specific domains, including dynamic graph generation and multi-modal RAG with contextual image retrieval. TF Mystica answers directly without a reasoning pass, favouring latency and throughput for low-thinking agentic work. A standard model in the extra-large tier on the priority serving route, served on ToothFairyAI's AU, EU and US endpoints — private by default, billed in US dollars per million tokens at the published rates below. No training on your data, no vendor lock-in.

AU · EU · US resident$2.34/1M input$7.02/1M output800K contextPriority serving

Run TF Mystica privately

One key, one endpoint, three jurisdictions.

  • Size tierExtra-large
  • Serving routePriority
  • Input rate$2.34/1M
  • Output rate$7.02/1M
  • Cached input rate—
  • Context window800K tokens
  • Max output16K tokens
  • ReasoningNo
  • Vision & video inputSupports image input
  • Tool callingSupported
  • Data residencyAU, EU and US endpoints — processing stays inside the region you call