Sovereign AI — JRAF by UBQT. Deploy, infer and experiment — your data stays in Canada.
From a simple API to fine-tuned models, everything stays in Canada.
Automatic routing to the optimal model (Lite → Standard → Pro) based on complexity.
Change one line of code, not your stack. Python, Node.js, curl SDK — everything works.
Native vector database to enrich responses with your data. 1 GB free.
Train a custom model on your data. Automatic deployment.
Data 100% in Canada, compliant with Law 25 and PIPEDA. Zero international transfer.
Available on the Inference API and for download on your dedicated GPU instances.
8B · 70B — Meta
7B · Mixtral 8x7B
7B · 32B · 72B
7B · 34B — Code
9B · 27B — Google
BGE · E5 · Nomic
Catalog constantly expanding. You can also deploy any Hugging Face-compatible model on your dedicated GPU instances.
All prices in CAD, before taxes (GST/QST).
| Model | Input (/1M tokens) | Output (/1M tokens) | Use case |
|---|---|---|---|
| JRAF Lite | 0.35 $ | 1.40 $ | Chatbot, classification, triage |
| JRAF Standard Popular | 1.50 $ | 6.00 $ | Writing, analysis, code, RAG |
| JRAF Pro | 8.00 $ | 32.00 $ | Complex reasoning, agents |
| Component | Price (CAD) |
|---|---|
| JRAF API access | Free |
| Embeddings | 0.05 $ per 1M tokens |
| Vector database (RAG) — 1 GB | Free |
| Additional vector storage | 0.10 $/GB/month |
| Fine-tuning (training) | 15.00 $ per 1M tokens |
| Fine-tuned model hosting | 2.00 $/h (active) · 0 $ (inactive) |
| Starter credit | 5.00 $ free |
Example: JRAF agent, 100 conversations/day (80% Lite, 20% Standard) ≈ $13/month. Compliant with Law 25 and PIPEDA.
Real use cases where Canadian hosting makes all the difference.
Analyze patient records, summarize medical reports, assist with diagnosis — with the guarantee that data stays in Canada and complies with provincial laws.
Case law research, contract analysis, assisted drafting. Your clients' confidential data protected by Canadian sovereignty.
Risk analysis, fraud detection, intelligent customer service. Canadian regulatory compliance ensured by data localization.
Automation of citizen services, document processing, policy analysis. 100% Canadian infrastructure for government requirements.
Deploy AI assistants on the Inference API with the OpenAI-compatible API. Migrate from OpenAI/Azure by changing a single URL.
Combine UBQT embeddings with your vector databases for intelligent search over your internal documents.
Your models run exclusively on Canadian infrastructure.
Here is what the Inference API experience looks like.
One key for all models on the Inference API.
OpenAI-compatible API — use the SDK you already know.
Change the base_url — the rest of your code stays the same.
Sign up to be notified when LLM / AI services become available.
We will only contact you for the launch. No spam.