Last refreshed 2026-10-30. Next refresh: weekly.
Why use joey-1 on Baseten API?
Baseten API offers joey-1 with pay-as-you-go pricing at $0.01/1M input tokens. Baseten is an AI infrastructure platform that provides comprehensive tools for deploying and serving machine learning models efficiently and cost-effectively.
Compare joey-1 across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: decision-models/baseten-joey-2b-latestdecision-models/baseten-joey-2b-latestRequest example
decision-models/baseten-joey-2b-latest.Gotchas
- Use provider model ID "decision-models/baseten-joey-2b-latest", not the LLMReference slug "joey-1".
Compare joey-1 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Baseten API | $0.01 | Free |
| OpenRouter | $0.01 | Free |
| Vercel AI Gateway | $0.01 | Free |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.01 |
| Output tokens | Free |
Capabilities
About joey-1
joey-1 is a 2B open-weight decision model from Base Labs, Baseten's research lab, released October 29, 2026. It is a fine-tune of Qwen3.5-2B that turns a state and typed questions into calibrated probabilities for choice, yes/no and score answers in a single forward pass, without generating free-form text, for routing, classification and rubric scoring. It accepts text and images and has a 16,384-token context limit. It is the smallest of Base Labs' three decision models (with elephant-1 and mammoth-1). Weights are on Hugging Face at baselabs/joey-1 under MIT.