PulseAugur
EN
LIVE 22:58:28

Baseten releases joey-1, a 2B decision model for high-volume tasks

By PulseAugur Editorial · [1 sources] ·

Baseten has introduced joey-1, a 2 billion parameter decision model developed by its Base Labs. This model is designed for high-volume tasks like routing and classification, outputting labels and calibrated probabilities rather than free-form text. It is based on Qwen3.5-2B and offers a low cost of $0.01 per million tokens, with open weights available on Hugging Face. AI

IMPACT Offers a low-cost, high-speed alternative for classification and routing tasks, potentially accelerating adoption in high-volume applications.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on MarkTechPost →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Baseten releases joey-1, a 2B decision model for high-volume tasks

How we ranked this

Signal score
63 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Baseten Releases joey-1, a 2B Decision Model at $0.01 per 1M Tokens

    <p>Baseten has released joey-1, a 2B open-weight decision model that returns calibrated probabilities instead of text. It runs at 20 ms P50 latency and costs $0.01 per million input tokens.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/29/baseten-joey-1-2b-decisio…

RELATED ENTITIES

RELATED TOPICS