Baseten launches joey-1: 2B decision model with 20ms P50 latency at $0.01/M tokens
baseten · x · 2026-10-30
Eight days after mammoth-1 (27B) and elephant-1 (9B), Baseten's Base Labs adds joey-1 (2B), its fastest and cheapest decision model: 20ms P50 end-to-end latency (2.5x faster than elephant-1), $0.01 per million tokens (a tenth of mammoth-1), and claimed best-in-class under 3B parameters, with text+image input. Decision models return a single token plus calibrated probability instead of generated text, slashing cost and latency in chained triage/flagging/approval workloads.
Related event: Baseten Open-Sources 2B Decision Model joey-1 with 20ms Latency(6 posts)→
More from Infra
- Even 2020-era GPUs keep gaining rental value, undercutting the AI bubble thesis — JFPuget · 2026-10-30
- Intel earnings call: server CPU TAM seen 5x to $200B+, chip shortage into 2028 — ryanshrout · 2026-10-30
- Lightweight FastAPI proxy gateway adds auth for locally hosted LLMs in OpenCode — Frizzy-MacDrizzle · 2026-10-30
- Nvidia reportedly in talks to backstop >$5B on Nscale's 460 MW site, locking in Anthropic's $45B Vera Rubin deal — ns123abc · 2026-10-30
- btrfs zstd compression cuts 35GB of daily agent JSON output to ~1/20 the disk space — mgostIH · 2026-10-30
- Rune launches 26B-A4B 'System One' decision model: no text generation, answers in one pass — sophiamyang · 2026-10-30