---
format: "aidr-story-markdown/v1"
id: "f38ccb0a6fd5a9a0ffc0e999063b81461fbed83f459c8857b4fa98a9941763b0"
canonical_url: "https://aidr.today/f38ccb0a?lang=en"
title: "Baseten Releases joey-1, a 2B Decision Model at $0.01 per 1M Tokens"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-29T21:20:29.000Z"
category: "Models"
topics: ["inference"]
source_urls: ["https://www.marktechpost.com/2026/10/29/baseten-joey-1-2b-decision-model/"]
summary: "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."
---

# Baseten Releases joey\-1, a 2B Decision Model at $0\.01 per 1M Tokens

> [Open the canonical story](<https://aidr.today/f38ccb0a?lang=en>)

**Published:** 2026-10-29T21:20:29.000Z
**Category:** Models
**Topics:** inference

## Summary

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\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/10/29/baseten-joey-1-2b-decision-model/>)