Baseten's Joey 1: a 2B decision model returning calibrated probabilities in a single forward pass
baseten · x · 2026-11-02
Baseten's research team Base Labs launched Joey 1 on OpenRouter, a 2B decision model post-trained from Qwen3.5-2B. Instead of generating text, it takes a state (text or JSON) plus typed questions (yes/no, multiple choice, or ordinal score) and returns calibrated probabilities for every option in a single forward pass.
- Pricing: $0.01/M input tokens, free output, 16K context.
- Positioned for high-volume routing, classification, and guardrail checks where latency and cost dominate; TypeSafe System One compatible.
- Larger siblings: Elephant 1 and Mammoth 1.
More from Models
- dbreunig: stop treating OpenRouter usage data as macro AI trends — dbreunig · 2026-11-03
- Frontier models flunk 1,000-variant DNA classification: refusals, token blowouts, encrypted reasoning — _lewtun · 2026-11-03
- GPT-6 Astra tops robot index, but finishes dual-arm sim task only twice in 800 trials — minchoi · 2026-11-03
- Qwen Head Dispels Rumors: Qwen 4.0 and 5.0 Will Stay Open Source — ResearchCrafty1804 · 2026-11-03
- Plus Subscriber Complaints About OpenAI's Opaque Usage Limits to UK's CMA — YouHadTooMuchToThink · 2026-11-03
- OpenAI's Cyber Guardrails Softlock a User's Legit Security Audit Mid-Task — Linuxxsxx · 2026-11-03