JEV / SYSTEM ONE
Uses the Jev decision playground
Send model: "baseten/groundhog-1", a shared text or JSON state and named Choice, Score or Noul questions to /v1/systemone. Add up to 4 shared image attachments when needed.
Now available: GPT-6 Luna Decisions
Try the modelBASE LABS / BASETEN / OPENROUTER
Base Labs’ Gemma 4 26B A4B (4B active MoE) decision model on Baseten. Evaluate text, JSON and images with typed Choice, Score and Noul questions in a single forward pass.
baseten/groundhog-1New accounts get 100 credits. The playground and API share one balance.
Context window
16,384
tokens · provider-listed maximum
OpenRouter input price
$0.035 / 1M
per million input tokens
OpenRouter output price
$0 / 1M
output tokens are free upstream
This site's input rate
500
credits per million input tokens · minimum 1 per successful request
JEV / SYSTEM ONE
Send model: "baseten/groundhog-1", a shared text or JSON state and named Choice, Score or Noul questions to /v1/systemone. Add up to 4 shared image attachments when needed.
SPAN / NOUL
Span-01 and Span-01 Lite accept only Noul behavior questions and require text or a specific input/output conversation object. General decision models also accept Choice and Score questions with text, JSON objects or arrays as state. Span-02 follows this broader decision contract and supports images in the shared decision playground.
Choice returns a named option and its probability distribution. Score returns a value on an ordered scale with probabilities. Noul returns the probability of a yes/no condition. Multiple questions share the same state.
Provider context: 16,384 tokens including state and questions. This service accepts up to 8 questions, 2–255 Choice options and 2–10 Score levels. Text plus questions must fit 32 KiB and the provider context. Up to 4 PNG, JPEG or WebP images: 4 MiB and 16 MP each, 8 MiB total; complete image requests up to 13 MiB.
Served by Baseten through OpenRouter. Groundhog 1 is the faster, lower-cost MoE sibling of Bison 1 in Base Labs’ Gemma 4 decision lineup. Compare both models on your own labeled examples.
OpenRouter input: $0.035 per million tokens. This service charges 500 credits ($0.05) per million actual input tokens, including questions and processed images. Output adds no charge. Successful calls round up to at least 1 credit ($0.0001); failed calls release the reservation.
max(1, ceil(input_tokens × 500 / 1,000,000))
A successful request with 1,000 input tokens costs 1 credit; 5,000 input tokens cost 3 credits. Output tokens add no charge. Failed calls release the credit reservation.
Checked November 21, 2026 with 10 live probes: text, JSON objects and arrays, all three answer types, 8 questions, 255 options, 10 score levels, a tail marker, red/blue images and 4-image input. All probes passed schema, input-cost and credit-reservation checks. These checks verify the API contract rather than accuracy or calibration.
The Jev workbench below starts with this model selected. Try a recipe, edit the state and questions, or export API code. This page stores its browser draft separately from other model pages and the main playground.
What do you want to decide?
Choose a task to load its input and rules. Loading examples uses no credits.
We reserve this budget before the model runs, then charge actual usage and return the difference. Failed calls are refunded. Microsoft Decision 1.1 and Liquid d1.2 Ultra: 600 credits/M; Liquid d1.2: 300 credits/M. Parallel Decisions Fast uses a fixed 15 credits ($0.0015) per successful request, independent of input-token usage; failed calls release the reservation. Groundhog 1: 500 credits/M input tokens; Bison 1: 1,500 credits/M input tokens (text, JSON and images; output free).
New account? Receive 100 credits once. Short requests typically use 1 credit; longer inputs can use more.
Draft saved in this browser · Your draft will be restored after sign-in.
Your current configuration stays in this browser tab for the setup flow.
ILLUSTRATIVE EXAMPLE · NO CREDITS USED
“I was charged twice this morning. Please refund the duplicate payment today.”
Choice
Billing
Route to the billing queue
Yes / no
96%
Probability of an urgent request
Score
2.8 / 3
Urgency on a 0–3 scale
Static illustration of the output format. Values are not a live model response or a measure of accuracy.
Capture A, change the model or questions in the workbench, then capture B. Both versions use identical states.
Capture A from the current workbench model and rules. Change the model or questions, then capture B. Import up to 25 labeled cases and compare both versions. The dataset state replaces each captured state.
This simulates a policy, not accuracy. Noul uses max(P(yes), P(no)); Choice and Score use your selected signal. Validate thresholds on labeled cases.
Total budget across both versions and all cases. Each request reserves its own allowance, then settles actual usage and refunds the remainder. Stopping preserves charges for completed requests.
New account? Receive 100 credits once. Short requests typically use 1 credit; longer inputs can use more.
Each successful comparison request uses credits. Review the total budget before starting. Requests run sequentially; stopping keeps charges for completed requests. Export includes rules, cases, results and errors. Closing this page stops the comparison.
Send model, state, and questions to Decisions API's /v1/systemone endpoint with an API key created here. Set model to baseten/groundhog-1; answers are in data.result.answers and token usage is in data.result.usage.
// Server-side JavaScript (Node 20+ or Bun). Set DECISIONS_API_KEY.
const response = await fetch("https://decisions-api.dev/v1/systemone", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.DECISIONS_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "baseten/groundhog-1",
"state": "I was charged twice for order A-4471. My account is blocked and I need access today. Please refund the duplicate payment.",
"questions": {
"route": {
"type": "choice",
"instructions": "Which team should handle this ticket? Use other when no option fits.",
"criteria": {
"billing": "Payments, charges and refunds",
"technical": "Bugs and product errors",
"account": "Login and account access",
"other": "None of these teams"
}
},
"urgency": {
"type": "score",
"instructions": "Rate the urgency using only the supplied ticket.",
"criteria": [
"Low: routine request",
"Medium: timely help needed",
"High: blocked or time-critical"
]
},
"needs_review": {
"type": "noul",
"instructions": "Does this ticket require a human to review a billing or account action?",
"criteria": {
"true": "A refund, payment correction or blocked account needs review.",
"false": "An informational request that needs no account or payment change."
}
}
}
}),
});
const body = await response.json();
if (!response.ok || body.code !== 0) throw new Error(body.message);
console.log(body.data.result.answers);
console.log(body.data.creditsUsed);