对比 · 参考
Jev 与 d1-ultra 对比
核验日期 2026 年 11 月 10 日。除非另有说明，价格为美元每百万输入 token，来自公开标价，不是报价或本站实测。
Jev 和 d1-ultra 都回答给定 state 中的类型化问题。比较时必须分开模型、接入渠道和实际负载。jevtypesafe.org 是独立 Jev 托管站，不是 TypeSafe AI 或 Liquid AI，本站文档没有列出 d1-ultra 接口。
能力取决于具体模型与渠道
Liquid 的其他开放权重 d1 变体有不同能力，不能套到 d1-ultra。官方 Jev 长上下文请求头也不代表本站实现了对应功能。
| Capability | TypeSafe Jev official | Jev on this host | Liquid d1-ultra official |
|---|---|---|---|
| Typed questions | Choice, Score, Noul; Box on 1.14 | Choice, Score, Noul; Image/Box beta, not recommended for production | Choice, Score, Noul |
| Input | Text and images | Text; images are beta | Text and images |
| Model selector | jev-1.14.0; jev-latest points to it | jev or omitted; upstream pinning not established here | d1-ultra in published API example |
| Endpoint | https://api.typesafe.ai/v1/systemone | https://jevtypesafe.org/api/v1/decide | https://api.liquid.ai/decisions/v1/systemone |
| Local weights | Not offered in reviewed official guide | No local deployment documented | Ultra classified as hosted, not open-weight download |
| Streaming or tool execution | Not established by reviewed System One contract | No support established by reviewed host contract | Not established by reviewed ultra sources |
三个计费渠道不能混成两个套餐
两家官方输入单价数值相同，不等于一次请求成本相同。本站零售价不是 Jev 官方标价。
| Channel | Input | Output | Conditions |
|---|---|---|---|
| TypeSafe official Jev 1.14 or 1.13 | $0.042/M | Free | Official model guide; separate official account and key |
| jevtypesafe.org hosted Jev | $0.175–$0.42/M | Free under host metering | Prepaid retail packs; $5 minimum listed; rates depend on pack size |
| Liquid official d1-ultra | $0.042/M; cached input also $0.042/M | $0.00/M | Current pricing page; each question billed as its own prompt |
购买前阅读本站价格页。
多问题会改变成本计算
Liquid 说明每个 d1-ultra 问题按独立 prompt 计费，包含问题文本与图片。HTTP 只传一次 state，账单仍可能多次计入共享内容。
纯文本假设：state 1,000 token、三问题各 100 token → 3×(1,000+100)=3,300 输入 token → $0.042/M 下 $0.0001386。假设计数，不是真实账单。
TypeSafe 文档称 state 摄入一次、问题并行。精确 Jev 账单看返回 usage。本站 multiplier 为 1，余额按 usage.billed_tokens。勿把 openai-decisions 的 3 倍扣款当成 Jev 或 d1-ultra 单价。
延迟来源不是同台对比
这些结果没有统一负载、地区、并发与分位数，不能按数字排速度。
| Evidence | Reported latency | What it does and does not show |
|---|---|---|
| Sardine, November 2 | Around 100 ms per Jev call, under 1,000 input tokens | A particular fraud workflow, not this host or a D1 comparison |
| arXiv v2, Jev 1.13 | Mean 0.36 s client-side, including network, at 32 concurrent requests | Published experiment on 37 datasets, not Jev 1.14 or this host |
| Encima, October 8 | Jev mean 0.41 s; Decisions API mean 0.52 s | Separate mixed-task comparison, not a d1-ultra test |
| Liquid d1-ultra release and reviewed docs | No comparable numeric latency figure established | Single forward pass is an architecture claim, not end-to-end p95 latency |
区分厂商评测与自己的评估
Liquid 10 月 15 日发布文称对 d1 与 Jev 1.14 做 112 项评估并宣称更好准确率与校准，属于厂商结论，不是本站独立实验。
在有权使用的固定数据上回放目标版本，记录模板、输入大小、问题数、图片尺寸、usage、错误、并发与地区，并测任务质量与 p50/p95。
使用判断与代码组合方法把策略留在模型外。通过 Playground 了解 Jev 模式，不是 D1 试用。
Sources
来源参考:
This is an unofficial community resource. We are not affiliated with TypeSafe AI or Liquid AI.