Typed output
Use choice, score, or noul results directly in branches, thresholds, and review gates.
Decision model
Use this model when your application has context and needs a clear, machine-readable signal before it routes, evaluates, or acts.
Use the exact model ID shown in this page. Credits follow the same Jev rule as the other decision models.
A decision boundary
respan/span-01-lite:freeState
A workflow has enough context to choose a safe next step.
Route to the approved path
0.84 confidence
Escalate if evidence is incomplete
Keep permissions, side effects, and final actions in your application.
Input
State + typed questions
Output
Choice · score · noul
Billing
Same as Jev
Endpoint
POST /v1/systemone
Why this model
Keep the model focused on one bounded judgment and let your application own everything that happens after it.
Use choice, score, or noul results directly in branches, thresholds, and review gates.
Record the state, question, answer, and confidence together for debugging and evaluation.
Treat the model as a signal; keep tools, permissions, writes, and side effects in code.
Where it fits
Start with a decision that has a small set of valid outcomes and an explicit fallback.
Routing
Choose a team, queue, or next step
Return an approved route
Evaluation
Score quality or readiness
Gate the next workflow
Safety boundary
Detect uncertainty or risk
Escalate before side effects
Call the model
Set the model ID shown on this page and keep the rest of the System One request unchanged.
curl -X POST https://thejevai.com/v1/systemone \
-H "Authorization: Bearer <API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "respan/span-01-lite:free",
"state": "A customer request needs a safe next step.",
"questions": {
"route": {
"type": "choice",
"instructions": "Choose the correct next step.",
"criteria": {
"continue": "Continue the approved workflow",
"review": "Send the case for human review"
}
}
}
}'Keep the API key on your server. The Playground uses the same request shape through your signed-in session.
Build with it
A typed signal is easiest to operate when the owner, allowed outcomes, and fallback are already clear.
Route a case while keeping the customer-facing action under application control.
Check a requested tool path before permissions and side effects are applied.
Turn a rubric into a score or noul signal for review and regression workflows.
FAQ
Set model to the exact ID shown on this page in the POST /v1/systemone request, or choose it in the Playground.
Yes. Supported decision models use the same Jev-based credit rule. Validate quality, latency, and availability with your own cases.
No. Use the response as a typed recommendation and keep tools, permissions, writes, and human review in your application.
References
Check current availability and provider-specific details before production use.
Follow the shared request, response, authentication, and error contract.
Measure route accuracy, confidence, latency, and review rate with representative cases.
Start with a bounded question
Try the model in the Playground, then move the same request to your server when the output is stable.