Base Labs ships joey-1, a 2B decision model with 20ms latency at $0.01/M tokens
baseten · x · 2026-10-30
Base Labs released joey-1 (2B), its third open-source decision model after mammoth-1 (27B) and elephant-1 (9B). Key points:
- Decision models return a single token plus calibrated probability instead of generating text, cutting cost/latency for routing, flagging, approval workloads
- P50 end-to-end latency of 20ms on 2,000-token requests (2.5x faster than elephant-1's 49ms, 5x faster than comparable models)
- Priced at $0.01 per million tokens, one-tenth of mammoth-1
- Claimed strongest decision model at ≤3B params; accepts text and images
- Available via Model APIs, dedicated deployments, and fine-tuning cookbook on Training Jobs.
More from Infra
- PC downturn frees wafers for server CPUs, not accelerators, argues Bajarin — BenBajarin · 2026-10-30
- Amazon misses on sales and EPS as AWS grows 39.3% but falls short of buy-side bar — Kr00ney · 2026-10-30
- Hands-on: Magnitude claims 2x over llama.cpp, but disappoints on mid/low-end hardware — OsmanthusBloom · 2026-10-30
- Fujifilm to boost 100TB tape production 5x with $63M, its biggest tape bet in 20 years, on AI demand — ControlCAD · 2026-10-30
- Altman: Memory Makers Could Each Make ~$100B Annual FCF but Won't Build Fabs — beffjezos · 2026-10-30
- Top-10 on a GPU kernel leaderboard: why agent kernel search pays back in ~6 months — JensHonack · 2026-10-30