Jev API —— 价格、怎么拿到,以及 apimodels 这边的现状

cURL

# 同类决策今天在 apimodels 上的做法:枚举 + 强制函数调用(2026-09-22 实测 3/3 通过)
curl https://api.apimodels.app/v1/chat/completions \
  -H "Authorization: Bearer $APIMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      { "role": "system", "content": "Route the support ticket to exactly one queue." },
      { "role": "user", "content": "Ticket: I was charged twice for my September invoice and need one of the payments refunded." }
    ],
    "tools": [{
      "type": "function",
      "function": {
        "name": "route_ticket",
        "description": "Send the ticket to one queue",
        "parameters": {
          "type": "object",
          "properties": {
            "queue": { "type": "string", "enum": ["billing", "bug", "feature_request", "account_access", "other"] }
          },
          "required": ["queue"]
        }
      }
    }],
    "tool_choice": { "type": "function", "function": { "name": "route_ticket" } }
  }'
# → choices[0].message.tool_calls[0].function.arguments == "{\"queue\":\"billing\"}"

Python

import json, os
from openai import OpenAI

client = OpenAI(base_url="https://api.apimodels.app/v1", api_key=os.environ["APIMODELS_API_KEY"])

QUEUES = ["billing", "bug", "feature_request", "account_access", "other"]
resp = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[
        {"role": "system", "content": "Route the support ticket to exactly one queue."},
        {"role": "user", "content": "Ticket: I was charged twice for my September invoice and need one of the payments refunded."},
    ],
    tools=[{
        "type": "function",
        "function": {
            "name": "route_ticket",
            "description": "Send the ticket to one queue",
            "parameters": {
                "type": "object",
                "properties": {"queue": {"type": "string", "enum": QUEUES}},
                "required": ["queue"],
            },
        },
    }],
    tool_choice={"type": "function", "function": {"name": "route_ticket"}},
)
queue = json.loads(resp.choices[0].message.tool_calls[0].function.arguments)["queue"]
print(queue)  # billing

现在能通过 apimodels.app 调 Jev 吗?

不能。截至 2026 年 9 月 22 日,我们的上游渠道都没有 Jev。我们正在接入,开放当天会更新本页;在那之前,我们不会用 Jev 的名字转发任何别的模型。

Jev API 兼容 OpenAI 格式吗?

不兼容。它有自己的接口 POST /v1/systemone:发送一个 state 和一组带类型的问题,返回带概率的答案。把 OpenAI SDK 直接指过去是用不了的;TypeSafe 提供了自己的 Python 和 JavaScript SDK。

做分类的话,Jev 比大模型便宜多少?

一次约 100 个输入 token 的决策,按 Jev 标价约 $0.000004,因为输出免费。同样的路由决策在 apimodels 上用 gemini-3.8-flash 做,连推理 token 在内我们实测约 $0.0002 —— 大约贵五十倍。如果你的 state 很长,差距会缩小,因为 Jev 对每个输入 token 都计费。

怎样才能从 Jev 的候补名单里被放出来?

TypeSafe 没有公布放号标准,开发者是分批从 console.typesafe.ai 的候补名单里被放进来的。如果你这周就需要能开发的东西,先在已经能调的模型上用强制函数调用把这个决策做出原型,并把标签组织成以后能直接对应 Jev 问题类型的结构。