Baseten releases 2B joey-1 decision model
AI · First reported 29 Oct, 17:49 · Updated 18:52

Baseten says joey-1 is designed for fast, high-volume decisions, with open weights and API pricing of $0.01 per million input tokens.
- The 2B model returns labels and calibrated probabilities rather than free-form text, and supports yes/no, multiple-choice and ordered-score questions.
- Baseten reports 20 ms P50 latency for an average 2,000-token request and a score of 63.30 on the Jev Decision Index 0.4 public split, ranking 37th of 230 models.
- The model is available through Baseten Model APIs and as MIT-licensed open weights; Baseten lists dedicated deployments with a 262k context window.
Summary written by Lux AI from 2 articles
Key facts
- Model size
- 2B parameters (7add5e2c-0739-4c51-87bc-61a61abdcfa6; fbcb7a06-84bf-44df-8b8d-9dd9496b51db)
- API price
- $0.01 per million input tokens (7add5e2c-0739-4c51-87bc-61a61abdcfa6; fbcb7a06-84bf-44df-8b8d-9dd9496b51db)
- Reported latency
- 20 ms P50 for an average 2,000-token request (7add5e2c-0739-4c51-87bc-61a61abdcfa6; fbcb7a06-84bf-44df-8b8d-9dd9496b51db)
- Jev Decision Index 0.4 public split
- 63.30; 37th of 230 models (7add5e2c-0739-4c51-87bc-61a61abdcfa6; fbcb7a06-84bf-44df-8b8d-9dd9496b51db)
- Weights
- Open under the MIT license (7add5e2c-0739-4c51-87bc-61a61abdcfa6; fbcb7a06-84bf-44df-8b8d-9dd9496b51db)
Source spectrum
Left 0 · Centre 2 · Right 0 of 2 rated sources
All coverage
Coverage over time
LeftCentreRight
Articles per hour since first reported, by side.
Ownership
- Corporation 100% (2)
Share of the 2 sources by owner type.