AI Agent StoreBaseten / Base Labs · Native API and download verified
Joey-1 · native API
Route support tickets, check a screenshot or rate a record against choices you define. Joey-1 is the small, low-price member of Base Labs’ decision family.
Released 2026-10-29 · First reviewed 2026-10-28 · Checked 2026-11-03.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact Native API ID: decision-models/baseten-joey-2b-latest. Returns yes/no probabilities, choices and ordered ratings. It does not write an explanation. The native API accepts text and images; test uncertain answers before allowing automatic actions.
Available through Baseten and as a 2B download derived from Qwen3.5-2B. The card labels the downloadable weights MIT; check the license included with your chosen package. Use the supplied CUDA serving setup and review the package terms.
The shared Model API allows 16,384 tokens per question including the shared information. The local card also states a 16,384 trained sequence length. A larger dedicated-deployment claim is not the shared API limit.
Native default input costs $0.01 per million tokens; output is free. Flex costs approximately 90% of default; priority defaults to twice the standard rate. These processing options do not establish measured speed gains. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Check whether confidence scores match the answers you can verify.
Compare caching and long-context costs ↗