The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
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, score, noul, classify, route
choice, classify, route
Architecture
decision
gpt-6-luna
Fine-tuned from
qwen/qwen3.5-9b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
OpenAI
Input price
—
—
Decision accuracy
77.4%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 decision and decisions-api?
decision is from vLLM Semantic Router and decisions-api from OpenAI. decision has open weights you can download and run; decisions-api is only available as a hosted API. Both answer choice, classify and route questions. Only decision answers score and noul. decision is licensed apache-2.0; decisions-api, proprietary.
Which is more accurate, decision or decisions-api?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decision or decisions-api?
decision: Free (open weights). decisions-api: Hosted, price not published. Open weights cost nothing per call beyond your own hardware.
Can I run decision or decisions-api locally?
decision yes — systemone pull vllm-semantic-router/decision downloads its weights. The other is only served as a hosted API.
