Jev Latest
Turn structured context into typed decisions, scores, and probabilities for classification and routing.
$0.0421 in / 1M
jev-latestJev Latest turns text into typed decisions instead of free-form chat replies. Describe the questions you need answered — a choice, a yes/no, or a score — and Jev returns each answer with probabilities your code can trust. It is billed on input tokens only.

The TypeSafe AI models most people start with. Prices are live and update automatically.
Turn structured context into typed decisions, scores, and probabilities for classification and routing.
$0.0421 in / 1M
jev-latestPick one label from your own list, such as refund, shipping, technical or other.
Flag urgency, spam, policy issues or anything else with a true/false answer.
Rate severity, quality or priority on a scale you define.
Each answer comes with probabilities, so you can set your own confidence thresholds.
You pay for the text you send. There is no output token charge.
Send tickets, messages or leads to the right queue, team or model automatically.
TokenRex sits between your app and TypeSafe AI. You send a normal API request with your TokenRex key; we check the key and your balance, pass the request to TypeSafe AI, stream the answer back, and bill the exact usage TypeSafe AI reports.
Your app
SDK, agent or BYOK tool
TokenRex
Checks key and balance
TypeSafe AI
Runs the TypeSafe AI model
Answer + bill
Streamed back, billed per use
Sign up with email or Google. New accounts can claim free starter credit.
Open API keys in your dashboard and create a key. Keep it private.
Set the base URL to https://tokenrex.ai/api/public in your SDK or BYOK app and paste your key.
Copy the exact model ID from the list on this page, for example from a flagship card.
Each request is billed at the live model price and deducted from your prepaid wallet.
cURL · Decisions API
curl https://tokenrex.ai/api/public/decisions \
-H "Authorization: Bearer YOUR_TOKENREX_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "jev-latest",
"state": "Customer says: my order never arrived and I want a refund.",
"questions": {
"category": {
"type": "choice",
"instructions": "Classify the support ticket.",
"criteria": { "refund": "Wants money back", "shipping": "Delivery problem", "other": "Anything else" }
}
}
}'Endpoints for TypeSafe AI models
POST /v1/decisionsTyped decisions with probabilities1 models in 1 families. Open a model to see every version, cache rates and limits.
Top up once and every request is deducted from your balance. No subscription and no monthly minimum.
If TypeSafe AI reports cached input tokens, they are billed at the model's lower cache-read rate.
Where offered, Fast versions answer about 2x faster at 2x the price.
A chat model writes free text. Jev answers the exact questions you define and returns typed values with probabilities, which is easier and safer to use in code.
On input tokens only, at the live price shown on the Jev Latest model page. There is no output charge.
Yes. Put multiple named questions in one request — for example a category, an urgency flag and a severity score.
TypeSafe AI and its logo are trademarks of their owner and are shown only to identify the models available. TokenRex is an independent service by Asirex Labs and is not affiliated with or endorsed by TypeSafe AI.