An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.
OpenAI's decision endpoint, announced at DevDay 2026. It focuses GPT-6 Luna on developer-defined questions that have a finite set of predefined answers, with text or image context, for classification, routing and an agent's next action.
Decides
choice, noul, score, classify, route
choice, classify, route
Architecture
nimble
gpt-6-luna
Fine-tuned from
qwen/qwen3.5-9b
—
License
apache-2.0
proprietary
Availability
Open weights + hosted API
Hosted API
Hosted by
Bespoke Labs
OpenAI
Input price
—
—
Decision accuracy
90.1%
—
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bespoke-nimble-9b and decisions-api?
bespoke-nimble-9b is from Bespoke Labs and decisions-api from OpenAI. bespoke-nimble-9b has open weights and a hosted API; decisions-api is only available as a hosted API. Both answer choice, classify and route questions. Only bespoke-nimble-9b answers noul and score. bespoke-nimble-9b is licensed apache-2.0; decisions-api, proprietary.
Which is more accurate, bespoke-nimble-9b or decisions-api?
Only bespoke-nimble-9b publishes an accuracy figure (90.1% on Bespoke held-out set (324 examples)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, bespoke-nimble-9b or decisions-api?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run bespoke-nimble-9b or decisions-api locally?
bespoke-nimble-9b yes — systemone pull bespoke-labs/bespoke-nimble-9b downloads its weights. The other is only served as a hosted API.
