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.
Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
gpt-6-luna
intern-decision
Fine-tuned from
—
qwen/qwen3.5-4b
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
OpenAI
—
Input price
—
—
Decision accuracy
—
80.6%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
44 ms
p95 latency
—
44.6 ms
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 decisions-api and intern-decision?
decisions-api is from OpenAI and intern-decision from InternLM (Shanghai AI Laboratory). decisions-api is only available as a hosted API; intern-decision has open weights you can download and run. Both answer choice, classify and route questions. Only intern-decision answers score and noul. decisions-api is licensed proprietary; intern-decision, apache-2.0.
Which is more accurate, decisions-api or intern-decision?
Only intern-decision publishes an accuracy figure (80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)); decisions-api does not, so there is no comparison to make without your own test.
Which is cheaper, decisions-api or intern-decision?
decisions-api: Hosted, price not published. intern-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisions-api or intern-decision locally?
intern-decision yes — systemone pull internlm/intern-decision downloads its weights. The other is only served as a hosted API.
Evaluation suite
—
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
