# Baseten — Decisions for a penny: introducing joey-1, our fastest decision model

- Company: Baseten (baseten.co)
- Announced: 2026-10-29T17:24:02+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1
- Record: https://forck.live/items/29451-decisions-for-a-penny-introducing-joey-1-our-fastest-decision-model
- Subject: Baseten
- Open weights: yes
- Models affected: joey-1, mammoth-1, elephant-1, Qwen3.5-2B
- Context window: 16k context window
- Pricing: $0.01 per million tokens

Baseten's research lab Base Labs has added joey-1, a 2B decision model it calls its fastest and most affordable, eight days after releasing mammoth-1 and elephant-1. Decision models return a label and a calibrated confidence score in one forward pass instead of generating text, which Base Labs says cuts the cost and latency that compound across chained decisions. In internal testing, joey-1 is the strongest decision model with 3B or fewer parameters, and at production scale it serves an average 2,000-token request at a P50 end-to-end latency of 20 ms, about 2.5x faster than elephant-1's 49 ms. At $0.01 per million tokens, joey-1 costs a tenth of mammoth-1; classifying 10 million support tickets a month at roughly 500 tokens each would run about $50 on joey-1 against $500 on mammoth-1. joey-1 is post-trained from Qwen3.5-2B using the same data and recipe as the larger models, and all three share one API, so switching between them is a one-line change. It is available now on Baseten Model APIs with a 16k context window and zero data retention by default, with open weights on Hugging Face; dedicated deployments reach the full 262k context window and support fine-tuned weights.

## Evidence

Verbatim from https://www.baseten.co/blog/decisions-for-a-penny-introducing-joey-1:

> A week ago we shipped mammoth-1 (27B) and elephant-1 (9B), the #1-ranked decision models. Today we’re adding joey-1, our fastest, cheapest 2B decision model.
> 
> Authors
> 
> Published
> 
> October 29, 2026
> 
> Share
> 
> Published
> 
> October 29, 2026
> 
> Eight days ago we released mammoth-1 (27B) and elephant-1 (9B), the #1-ranked decision models. Today we’re adding joey-1 (2B), our fastest and most affordable decision model, with a P50 latency of 20 ms, 5x faster than comparable decision model models.
> 
> Many LLM use cases don’t need generated text; they need decisions:
> 
> Where should this ticket go?
> 
> Should this message be flagged?
> 
> Should this request be approved?
> 
> LLMs have historically answered these by generating text, which adds cost and latency to every call, and that overhead compounds with each decision in a chain. Decision models return the answer directly as a single token and a calibrated probability score, drastically reducing cost and latency.
> 
> LLMs now come in many shapes and sizes, from full-scale models to flash and fast variants, because every workload weighs intelligence, speed, and cost differently. Decision models should too.

---

Record: https://forck.live/items/29451-decisions-for-a-penny-introducing-joey-1-our-fastest-decision-model
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md