{"version":1,"type":"story","url":"https://digestai.news/story/baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio","json":"https://digestai.news/story/baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio.json","markdown":"https://digestai.news/story/baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio.md","slug":"baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio","headline":"Baseten releases 2B-parameter decision model joey-1 at $0.01 per million tokens","summary":"Baseten launched **joey-1**, a 2 billion-parameter decision model from its research lab Base Labs, on October 29, 2026. Priced at **$0.01 per million input tokens**, it joins the company’s existing **mammoth-1 (27B)** and **elephant-1 (9B)** models, all trained on the same data mixture and sharing the same API for seamless switching. Unlike generative AI models, joey-1 returns a **label and confidence score** in one forward pass, designed for high-volume, latency-sensitive tasks like ticket routing or spam detection.\n\nBaseten claims joey-1 is **2.5x faster** than elephant-1 at serving 2,000-token requests (20ms latency) and the strongest 2B model on the **Jev Decision Index 0.4**, scoring **63.30** (37th overall). It supports three question types: yes/no, multiple-choice, and ordered scoring. The model is available via **Baseten Model APIs** and open weights on Hugging Face under the MIT license. Dedicated deployments offer a **262k context window** and fine-tuning capabilities. Training used **6.21 million decision examples** from a mixture called Mix 8, with a fine-tuning recipe optimized for low-latency inference.","keyPoints":["joey-1 is a 2B-parameter decision model priced at $0.01 per million input tokens, 10x cheaper than mammoth-1","Baseten claims it’s the fastest 2B model on Jev Decision Index 0.4, scoring 63.30 with 20ms latency for 2k tokens","Open weights released under MIT license; supports high-volume tasks like ticket routing and spam detection"],"whyItMatters":"A low-cost, high-throughput decision model like joey-1 could shift workloads from expensive LLMs to specialized models for cost-sensitive applications like customer support or fraud detection.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Baseten","Base Labs"],"models":["joey-1","mammoth-1","elephant-1","Qwen3.5-2B","Cloudflare Clef","Jev 1.14"],"people":[]},"firstPublishedAt":"2026-10-29T17:49:03Z","updatedAt":"2026-10-29T17:49:03Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Baseten Releases Joey-1, a 2B Open-Weights Decision Model","url":"https://unite.ai/baseten-releases-joey-1-a-2b-open-weights-decision-model","publishedAt":"2026-10-29T17:49:03Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Baseten releases 2B-parameter decision model joey-1 at $0.01 per million tokens\", 29 October 2026, https://digestai.news/story/baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio","publisher":"Digest AI","title":"Baseten releases 2B-parameter decision model joey-1 at $0.01 per million tokens","datePublished":"2026-10-29T17:49:03Z","url":"https://digestai.news/story/baseten-releases-2b-parameter-decision-model-joey-1-at-0-01-per-millio"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}