The fast model, when speed matters more than thinking.
Our everyday model. Bilingual, low-latency, tuned for drafting, summarization, translation, and quick answers. Free on every plan.

Fast · Everyday
Built for now-not-later
Fast. Capable. Sovereign.
Class
Fast
Languages
EN + QC FR
Latency
Low
Tier
Free + paid
Three places Tofino 2.5 shines.
Drafting + summarization
Email drafts, meeting summaries, document précis. Fast turn-around with a clean, professional voice. Edit and ship.
Bilingual translation
EN ↔ Quebec French in standard written register. Faster than the reasoning model for back-and-forth translation work.
Quick answers
When you need an answer in seconds, not paragraphs. Tofino 2.5 sits behind the free tier and the everyday chat surface.
Put it to work today, or scope a custom deployment.
Tuned for speed, without giving up the basics.
Tofino 2.5 is the everyday model. Smaller than Ossington 4 but tuned for low-latency response on the kinds of tasks that don't need extended reasoning — drafting, translation, summarization, quick retrieval-style answers.
Bilingual EN + Quebec French is native: same training treatment as Ossington, just at a smaller scale. The trade is speed for depth — when you need careful multi-step thinking, route to Ossington 4. When you need an answer now, Tofino 2.5 ships it.
Available on every Augure plan including the free tier. The fast model is part of the platform's baseline, not a paywalled tier.
Tofino 2.5 across the platform.
Try Tofino 2.5 free.
Free tier on every plan. Bilingual by default. Sovereign by architecture.