In the news
Decisions for a penny: introducing joey-1, our fastest decision model
Baseten · Published · 3 min read
In 30 seconds
- What happened
- Baseten released joey-1, a 2-billion-parameter decision model with 20ms latency, five times faster than comparable models.
- Why it matters
- Engineers building high-volume classification systems where latency and cost matter more than maximum accuracy.
- Watch out
- Decision models return single tokens, not generated text. They work only for classification tasks, not open-ended generation or reasoning.
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.