모델
Compare
Jev
Compare
TypeSafe logo

Jev

jev-latestllms.txt
TypeSafe
Jev is a structured decision model launched by TypeSafe and is also their first "System One" model. System One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.

Pricing

  • Input Tokens: $0.0462 /M tokens
  • Output Tokens: $0 /M tokens

입력 방식

  • Text
  • Vision

Context length

  • 64K tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

제공업체

TypeSafe jev-latest
Pricing$0.0462$0
PrecisionⓘNot Disclosed
Latency-
Throughput-
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
100.00% uptime today

Performance for jev-latest

Uptime은 지난 72시간 동안 성공한 요청의 비율입니다. AIHubMix는 모든 공급자를 지속적으로 모니터링하며, 오류가 발생하거나 응답이 느린 경우 자동으로 차선의 공급자로 재시도합니다; Latency는 요청의 총 왕복 시간입니다(낮을수록 좋음); Throughput은 모델의 출력 속도입니다(초당 토큰 수, 높을수록 좋음).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
import requests

# Structured decision: POST /v1/systemone — every question is evaluated in parallel and in
# isolation against the same state, and comes back typed. No text generation, nothing to parse.
# The answers{} map is keyed by your own question names; each answer holds its value under a
# key named after its type:
#   noul   -> { type, noul }                                      probability of "yes", 0..1
#   choice -> { type, choice, probabilities, confidence }          choice is one of your criteria keys
#   score  -> { type, score, legend, probabilities, confidence }   legend maps level index -> description
# usage carries input_tokens / output_tokens.
url = "https://aihubmix.com/v1/systemone"
headers = {
    "Authorization": "Bearer " + os.environ["AIHUBMIX_API_KEY"],
    "Content-Type": "application/json",
}
payload = {
      "model": "jev-latest",
      "state": "Hi, I have been trying to connect my Stripe account for 3 days and it keeps failing. I am losing sales. Please help ASAP.",
      "questions": {
        "department": {
          "type": "choice",
          "instructions": "Which team should handle this",
          "criteria": {
            "billing": "Payment or subscription issues",
            "technical": "Bugs or integration problems",
            "sales": "Pricing or account questions"
          }
        },
        "frustration": {
          "type": "score",
          "instructions": "How frustrated the customer appears",
          "criteria": [
            "Calm, just stating facts",
            "Frustrated but civil",
            "Very angry, strong language"
          ]
        },
        "is_urgent": {
          "type": "noul",
          "instructions": "The message conveys urgency or time-sensitivity"
        }
      }
    }

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()

data = response.json()
for name, answer in data["answers"].items():
    kind = answer["type"]
    print(name, kind, answer[kind], answer.get("confidence"))
print("usage:", data.get("usage"))

Frequently asked questions

What is Jev?

Jev is a structured decision model launched by TypeSafe and is also their first "System One" model. System One models can make structured decisions for software quickly, returning typed selection results rather than freely generated text. They are suitable for routing, classification, and other decision nodes in applications—where fast, predictable answers are more important than generating natural language content.