basetenListed Oct 29, 2026

Baseten: Joey 1

Joey 1 is a 2B decision model from Base Labs, Baseten's research team, built on Qwen3.5-2B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal...

Read full description

Joey 1 is a 2B decision model from Base Labs, Baseten's research team, built on Qwen3.5-2B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits high-volume routing, classification, and guardrail checks where latency and cost matter most. Its larger siblings are Elephant 1 and Mammoth 1.

Source description ↗Checked
Context window16.4K
Max output14.7K
Provider endpoints1
Benchmark results0

Model overview

Baseten: Joey 1 is a decision model from baseten. Listed capabilities include image input and open weights. The listed context window is 16,384 tokens.

Provider options and prices

Current standard quotes use 1M tokens. 1 listed provider option. Provider details and conditions →

  • OpenRouter ↗$0.01 input · $0.00 output / 1M tokens · USDCurrent standard quote
    Endpoint and conditionsbaseten/joey-1

    Configuration not reported.

    Quote source ↗ · Checked

Benchmark coverage

No published model benchmark result is linked to this exact identity in the catalog.

Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

1 quote
Input
$0.01
Output
$0.00
USD / 1M tokens
16.4K context14.7K max outputPrice source ↗Checked Oct 29, 2026
Endpoint IDbaseten/joey-1

Model specifications

Developer
baseten
Modality
Decision
Context
16,384 tokens
Maximum output
14,745 tokens
Weights
Open weights
Provider listed
Oct 29, 2026
First discovered
Oct 29, 2026

Exact identities

  • openrouterbaseten/joey-1

Sources

Updated Oct 29, 2026

More from baseten

View all ↗
basetenListed 7 days ago

Baseten: Mammoth 1

Mammoth 1 is a 27B decision model from Base Labs, Baseten's research team, built on Qwen3.5-27B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal...

16.4K contextImage inputOpen weightsNo reported score
No reported score
$0.10in$0.00out/ 1M tokens · USDOpenRouter
basetenListed 7 days ago

Baseten: Elephant 1

Elephant 1 is a 9B decision model from Base Labs, Baseten's research team, built on Qwen3.5-9B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal...

16.4K contextImage inputOpen weightsNo reported score
No reported score
$0.035in$0.00out/ 1M tokens · USDOpenRouter