typesafe/jev-1.13
Release date: 2026-09-18
32,000 context · $0.04/M input tokens · $0.05/M output tokens
Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather...
Pay-per-use
No upfront costs, pay only for what you use
Evaluate the same state with Choice, Score and Noul questions. Each question returns a structured answer.
curl --fail-with-body --connect-timeout 10 --max-time 120 \
https://llm.wavespeed.ai/v1/decisions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-d @- <<'JSON'
{
"model": "typesafe/jev-1.13",
"state": "My payment was charged twice. Please fix it today.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"billing": "Payments and invoices",
"technical": "Software bugs"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this request?",
"criteria": [
"Can wait",
"Needs attention today",
"Immediate emergency"
]
},
"duplicate_charge": {
"type": "noul",
"instructions": "Does this report a duplicate charge?"
}
}
}
JSONEvaluate the same state with Choice, Score and Noul questions. Each question returns a structured answer.
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const response = await fetch('https://llm.wavespeed.ai/v1/decisions', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.WAVESPEED_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "typesafe/jev-1.13",
"state": "My payment was charged twice. Please fix it today.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"billing": "Payments and invoices",
"technical": "Software bugs"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this request?",
"criteria": [
"Can wait",
"Needs attention today",
"Immediate emergency"
]
},
"duplicate_charge": {
"type": "noul",
"instructions": "Does this report a duplicate charge?"
}
}
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const response = await fetch('https://llm.wavespeed.ai/v1/decisions', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.WAVESPEED_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "typesafe/jev-1.13",
"state": "My payment was charged twice. Please fix it today.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"billing": "Payments and invoices",
"technical": "Software bugs"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this request?",
"criteria": [
"Can wait",
"Needs attention today",
"Immediate emergency"
]
},
"duplicate_charge": {
"type": "noul",
"instructions": "Does this report a duplicate charge?"
}
}
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather...
Send state and named questions to POST https://llm.wavespeed.ai/v1/decisions with your WaveSpeed API key as a Bearer token. Each answer is returned under its question name. Requests are non-streaming.
choice: select an option and return its probability distribution and confidence.score: evaluate ordered levels and return a score, legend, probabilities and confidence.noul: return the probability that a statement is true.State and instructions accept a string, JSON object or array. Questions share the same state and are evaluated independently.
{
"model": "typesafe/jev-1.13",
"questions": {
"billing_issue": {
"instructions": "Is this a billing issue?",
"type": "noul"
}
},
"state": "My invoice was charged twice. Please help."
}| Specification | Value |
|---|---|
| Model | typesafe/jev-1.13 |
| Model Type | Decisions |
| Context Window | 32000 tokens |
| Token Type | Cost per million tokens |
|---|---|
| Input | $0.042 |
| Output | $0.05 |
The response includes usage.input_tokens, usage.output_tokens and usage.cost. Cost reflects your applicable price and discount.
typesafe/jev-1.13
Jev is a structured decision model from TypeSafe, and the first of its System One models. System One models make fast, structured decisions for software, returning a typed choice rather...
Input
$0.042 /M
Output
$0.05 /M
Context
32K
Access Jev 1.13 through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Pricing on WaveSpeedAI: $0.04 per million input tokens and $0.05 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
Jev 1.13 supports up to 32K tokens of context with up to — tokens of output per request.
WaveSpeedAI exposes Jev 1.13 at https://llm.wavespeed.ai/v1 through the OpenAI-compatible Chat Completions interface. Most OpenAI SDK clients work by changing the base URL and API key; optional fields depend on the selected model.
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with the model id shown above. Check the current model catalog for availability, capabilities, and pricing.