typesafe/jev-1.13 API

typesafe/jev-1.13 is a model that you can call through the ScalingTensor API. Chat models available through the ScalingTensor API.

Chat

Provider

typesafe

Billing

Per token

ScalingTensor price

From $0.042 per 1M input tokens; output, cache and context tiers priced separately

Playground

Try typesafe/jev-1.13

Edit the example parameters, add your API key and run the model here. The response and usage appear on this page.

Input

Used for this request only and never stored. Get a key

Running a request charges your wallet: From $0.042 per 1M input tokens; output, cache and context tiers priced separately.

Output

preview

Request summary

Endpoint
POST /api/chat/completion
Model ID
typesafe/jev-1.13
state
{"ticket":"I was charged twice and would like a refund."}
questions
{"refund_requested":{"type":"noul","instructions":"Does the ticket explicitly request a refund?"}}

Need job lookups or the raw response? Open the full playground.

Pricing

typesafe/jev-1.13 API pricing

Prices come from the live catalog. There is no subscription; each request is charged to your prepaid wallet.

ScalingTensor price

Per token

Live catalog price

From $0.042

per 1M input tokens; output, cache and context tiers priced separately

USD per 1M tokens

TierInputOutputCache readCache write1h writeImage output
base$0.042$0$0.042$0.042$0.042—
Context thresholds and full pricing rule

p = uncached input, c = output, cr = cache read, cc = cache write, cc1h = one-hour cache write, img_o = image output. len is the full input context length, including cached tokens.

tier("base", p * 0.042 + c * 0 + cr * 0.042 + cc * 0.042 + cc1h * 0.042)
Compare all model prices

Shared balance

Add credits

Top up

One wallet and one API key for every model in the catalog. Top-ups start at $10 and are paid through Stripe.

Capabilities

What you can do with typesafe/jev-1.13

Parameters

Input parameters

Send model and the parameters shown below directly in the request body.

Input parameters
nametyperequireddescription
stateanyRequiredState passed to the System One model. The upstream accepts the native TypeSafe state shape.
questionsobjectRequiredTyped questions evaluated against state.

Output fields

Output fields
nametypedescription
idstringUnique identifier for this request
modelstringModel used for the request
answersobjectOne answer per question id (keys match your questions)
answers[].typestringAnswer type: choice, score, or noul
answers[].choicestringchoice: the selected option key
answers[].scorenumberscore: probability-weighted mean of level indices (a decimal)
answers[].noulnumbernoul: probability of "yes" (0.0-1.0)
answers[].probabilitiesobjectchoice/score: probability per option or level index
answers[].confidencenumberchoice/score: how peaked the distribution is (0-1); absent for noul
answers[].legendobjectscore: maps level index to your label
usage.input_tokensintegerTokens in the input
usage.output_tokensintegerTokens in the output

API

Call typesafe/jev-1.13 from your code

Create a key in the console and call POST /api/chat/completion with the apiKey header, model and the example parameters. A code of 0 means success; read data.content for the response.

POST /api/chat/completion
curl --request POST 'https://restapi.scalingtensor.com/api/chat/completion' \
  --header 'apiKey: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "state": {
    "ticket": "I was charged twice and would like a refund."
  },
  "questions": {
    "refund_requested": {
      "type": "noul",
      "instructions": "Does the ticket explicitly request a refund?"
    }
  },
  "model": "typesafe/jev-1.13"
}'
const response = await fetch("https://restapi.scalingtensor.com/api/chat/completion", {
  method: "POST",
  headers: {
    apiKey: process.env.SCALINGTENSOR_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "state": {
      "ticket": "I was charged twice and would like a refund."
    },
    "questions": {
      "refund_requested": {
        "type": "noul",
        "instructions": "Does the ticket explicitly request a refund?"
      }
    },
    "model": "typesafe/jev-1.13"
  }),
});

const result = await response.json();
if (!response.ok || result.code !== 0) {
  throw new Error(result.msg || `Request failed: ${response.status}`);
}
console.log(result.data); // Read content, tokensIn, tokensOut and costMicros
import os
import requests

payload = {
    "state": {
        "ticket": "I was charged twice and would like a refund.",
    },
    "questions": {
        "refund_requested": {
            "type": "noul",
            "instructions": "Does the ticket explicitly request a refund?",
        },
    },
    "model": "typesafe/jev-1.13",
}

response = requests.post(
    "https://restapi.scalingtensor.com/api/chat/completion",
    headers={"apiKey": os.environ["SCALINGTENSOR_API_KEY"]},
    json=payload,
    timeout=60,
)
result = response.json()
if result["code"] != 0:
    raise RuntimeError(result["msg"])
print(result["data"])  # Read content, tokensIn, tokensOut and costMicros

API documentation · This page as Markdown · Markdown API reference

Related models

typesafe/jev-1.13 API FAQ

How much does the typesafe/jev-1.13 API cost?

typesafe/jev-1.13 costs From $0.042 per 1M input tokens; output, cache and context tiers priced separately on ScalingTensor. There is no subscription; usage is charged to your prepaid wallet.

How do I call the typesafe/jev-1.13 API?

Send POST /api/chat/completion with "model": "typesafe/jev-1.13" and a messages array using your apiKey header. Read data.content from the successful response. Usage is reported in tokensIn, tokensOut and costMicros.

Which parameters does typesafe/jev-1.13 accept?

Required: state and questions. The parameter table on this page describes each one.

Do I need a typesafe account to use typesafe/jev-1.13?

No. You call typesafe/jev-1.13 with your ScalingTensor API key and pay from your ScalingTensor wallet. The same key works for every other model in the catalog.