Jev API —— 价格、请求格式,以及怎么在 apimodels 上调用

cURL

curl https://api.apimodels.app/v1/systemone \
  -H "Authorization: Bearer $APIMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jev",
    "state": "Support ticket: I was charged twice for my September invoice and need one of the payments refunded.",
    "questions": {
      "queue": {
        "type": "choice",
        "instructions": "Which support queue should handle this ticket?",
        "criteria": {
          "billing": "Payments, invoices, charges and refunds",
          "bug": "Something in the product is broken",
          "account_access": "Login, password or permission problems",
          "other": "Anything else"
        }
      },
      "urgent": {
        "type": "noul",
        "instructions": "The customer needs a response within the hour."
      }
    }
  }'
# → {"model":"jev-1.13.0",
#    "answers":{"queue":{"type":"choice","choice":"billing","confidence":1.0,
#                        "probabilities":{"bug":0.0,"other":0.0,"account_access":0.0,"billing":1.0}},
#               "urgent":{"type":"noul","noul":0.29}},
#    "usage":{"input_tokens":385,"output_tokens":63}}      # 385 input tokens ≈ $0.0000193

Python

# pip install typesafe-sdk   (TypeSafe's official SDK — only base_url and the key change)
import os
from typesafe_sdk import Choice, Noul, TypeSafeClient

with TypeSafeClient(
    base_url="https://api.apimodels.app",
    api_key=os.environ["APIMODELS_API_KEY"],
) as client:
    result = client.system_one(
        state="Support ticket: I was charged twice for my September invoice and need one of the payments refunded.",
        questions={
            "queue": Choice(
                instructions="Which support queue should handle this ticket?",
                criteria={
                    "billing": "Payments, invoices, charges and refunds",
                    "bug": "Something in the product is broken",
                    "account_access": "Login, password or permission problems",
                    "other": "Anything else",
                },
            ),
            "urgent": Noul(instructions="The customer needs a response within the hour."),
        },
    )

print(result.choices["queue"].choice)   # billing
print(result.nouls["urgent"].noul)      # a probability, e.g. 0.28

能通过 apimodels.app 调 Jev 吗?

可以。用你的 apimodels key 发 POST https://api.apimodels.app/v1/systemone,"model" 填 "jev"。请求和响应与 TypeSafe 官方 API 完全一致,把 TypeSafe 官方 SDK 的 base_url 指向 https://api.apimodels.app 就能用。不需要 TypeSafe 账号。

apimodels 上的 Jev 比官方贵多少?

我们是输入每百万 token $0.05,TypeSafe 官方标价 $0.042;两边输出都免费。一次 400 token 的典型决策在我们这里花 $0.00002,一百万次这样的决策在我们这里 $20、直接找官方 $16.80。我们按实际 token 计费、没有每次最低收费,调用失败不收钱。

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;请用 TypeSafe 官方 SDK 配我们的 base URL,或者像 cURL 示例那样直接发 HTTP 请求。

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,在 apimodels 上用 Jev 约 $0.000005,因为输出免费。同样的路由决策用 gemini-3.8-flash 加强制函数调用,连推理 token 在内我们实测约 $0.0002 —— 大约贵四十倍。如果你的 state 很长,差距会缩小,因为 Jev 对每个输入 token 都计费。

Jev 调用失败或被限流时会怎样?

不收钱。请求本身的问题(HTTP 400 或 422)会带着 TypeSafe 原本的报错信息返回,方便你修改。被限流时返回 429、code 为 rate_limited,请按指数退避重试。上游故障返回 502,可以放心重试。

Jev 还需要排队吗?

不需要。TypeSafe 在 2026 年 9 月 20 日取消了候补名单;apimodels 这边从来没有排队:注册、在控制台创建 API key、充值,然后调用 /v1/systemone 即可。