Sovereign inference — TF Sorcerer

Your sovereign, private TF Sorcerer

TF Sorcerer is ToothFairyAI's proprietary model system: a production-grade orchestration layer over a curated ensemble of open-source foundations and our own fine-tuned models. A custom-trained router analyses every request in real time — task complexity, required capabilities, latency and cost constraints — and dispatches it to the specialist model best suited to the job, with continuous health-aware failover across providers. TF Sorcerer answers directly without a reasoning pass, optimised for speed and cost on everyday chat and tasks. A standard model in the medium 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$0.63/1M input$2.27/1M output$0.16/1M cached input800K contextPriority serving

Run TF Sorcerer privately

One key, one endpoint, three jurisdictions.

  • Size tierMedium
  • Serving routePriority
  • Input rate$0.63/1M
  • Output rate$2.27/1M
  • Cached input rate$0.16/1M
  • 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