人人用得起的 AI AI that everyone can afford

还不能。机器一台没买，现在只登记意向，不收任何人的钱。满 80 个真的想用的人，我们就去买机器、开机，第一批邀请发给登记的人。不满 80，说明这件事现在还不该做，我们继续等。Not yet. No hardware has been bought and we take no money at this stage — we are only collecting interest. At 80 people who actually want this, we buy the hardware and turn it on, and the first invites go to the list. Below 80, we keep waiting.

为什么是 80？因为这个规模能让我们把机器开起来、并撑住前三个月的运营。达不到就是白烧钱，我不想那样开始。Why 80? Because that is the scale at which the machine can be switched on and kept running for the first three months. Below it, we would just be burning money — and I would rather not start that way.

是模型原生窗口，不是外推。我们已在 262,144 token 的文档上做过针检索测试：埋在全文 33%、66%、90% 位置的三段信息全部按序取回。上游引擎的实测上限更高（在该硬件上可开到 66 万至 97 万 token）。It is the model's native window, not extrapolation. We ran a needle test on a 262,144-token document: codes planted at 33%, 66% and 90% were all retrieved in order. The upstream engine has been measured even higher on this hardware — 660k to 970k tokens.

Ternary Bonsai 2 27B，基于 Qwen3.8-27B 架构以三元权重原生训练（{-1, 0, +1}），配 FP16 分组缩放，权重约 5.9GB，官方基准保留全精度模型 98.2% 的综合能力。权重以 Apache 2.0 开源，你也可以自行部署。Ternary Bonsai 2 27B — natively trained with ternary weights ({-1, 0, +1}) on the Qwen3.8-27B architecture, with FP16 group scales. About 5.9 GB of weights, retaining 98.2% of the full-precision model's aggregate benchmark score. Released under Apache 2.0, so you can self-host it too.

便宜来自三件事：模型只有 7GB 出头（一张消费级显卡就能跑）、三元权重让显存带宽瓶颈大幅缓解、我们用批量并发把单卡利用率拉满。质量上，它在公开基准池拿 84.4/100，做分类、抽取、摘要、翻译、客服问答这类任务和前沿模型差距很小；但复杂推理、长链路 Agent、难题编程明显不如 Opus 4.6。Three things: the model is just over 7 GB (it runs on a single consumer GPU), ternary weights relieve the memory-bandwidth bottleneck, and we batch requests to keep utilization high. On quality it scores 84.4/100 on a public benchmark pool — close to frontier models on classification, extraction, summarization, translation and support Q&A, but clearly behind Opus 4.6 on complex reasoning, long-horizon agents and hard coding.

服务端按前缀精确匹配复用 KV 缓存。响应 usage 中区分 prompt_cache_hit_tokens 与 prompt_cache_miss_tokens，分别按 ¥0.01/M 与 ¥0.20/M 计费。固定系统提示词、同一份长文档的多轮追问、Agent 的重复上下文都能命中。We do exact prefix matching on the server and reuse the KV cache. The usage block separates prompt_cache_hit_tokens from prompt_cache_miss_tokens, billed at $0.002/M and $0.20/M respectively. Fixed system prompts, follow-up questions on the same long document and repeated agent context all hit.

我们会按需增加 GPU 实例，但新增实例需要「拉起机器 → 拉取 8.87GiB 模型权重 → 预热」，约 5–10 分钟。满载时新请求会进入队列并按提交顺序处理，不会丢失。如果你有可预期的峰值，提前告知我们会事先扩容；紧急情况也可以通过控制台申请优先通道。We add GPU instances on demand, but a new instance has to boot, pull the 8.87 GiB model artifact and warm up — roughly 5–10 minutes. When saturated, new requests queue in submission order and are never dropped. Tell us about expected peaks and we scale ahead of time; you can also request a priority lane from the console.

算，但按成本折算成"单位"。1 个输出 token = 1 单位；输入 token（≤64K）只算 0.16 单位；长文档输入（>64K）算 0.35 单位；缓存命中只要 0.02 单位。所以把系统提示词和长文档交给缓存，额度几乎不掉。完整换算表在上面的"按量付费"一节。Yes, but converted into units by cost. 1 output token = 1 unit; input tokens under 64K cost 0.16 units; long-document input above 64K costs 0.35 units; cache hits cost just 0.02 units. Reuse your system prompt and long documents through the cache and your quota barely moves. Full table is in the pay-as-you-go section above.

随时可退，按未使用天数比例退款。当月未用完的额度可结转一个月（第二个月底清零）。额度用完后不会停服，会自动转按量付费，你也可以在控制台设一个月度封顶自动停。Cancel anytime with a pro-rata refund for unused days. Unused quota rolls over for one month and expires at the end of the following month. When the quota runs out we do not stop you — you roll onto pay-as-you-go, and you can set a monthly spend cap in the console.

三点：没有 5 小时滚动窗口，没有每周限额，价格便宜一个数量级。传统订阅撞到周限后只能等满 7 天、升级或转 API；我们额度用完后自动转按量付费，不降速、不断服。而且我们不绑定客户端——Claude Code、Cline、Cursor 改个 base_url 就能接到我们这里。Three things: no 5-hour rolling window, no weekly cap, and an order of magnitude cheaper. On a classic subscription, hitting the weekly cap means waiting seven days, upgrading, or switching to API billing; with us the quota simply rolls into pay-as-you-go with no throttle and no cut-off. And we are not tied to a client — point Claude Code, Cline or Cursor at our base_url and you are done.

会。捐款的 95% 进入额度池，用于增加算力和统一上调三档额度——上调对全体用户生效，包括没有捐款的用户，也包括你。剩下的 5% 用于支付通道手续费与账务成本。每月 1 号公示上月收到的金额、进入额度池的金额，以及额度实际提升了多少。额度池按累积制计算，累计达标后 30 天内完成上调。Yes. 95% of every donation goes into the quota pool, which is spent on adding capacity and raising all three plan quotas — the increase applies to every user, including those who never donated, and including you. The remaining 5% covers payment processing and accounting. On the 1st of each month we publish the total received, the amount that went into the pool, and how much the quotas actually rose. The pool is cumulative: increases land within 30 days of crossing a threshold.

捐款不产生任何额外权益：不会给你更多额度、不会插队、不会解锁功能。额度池的余额和流水在控制台随时可查。这不是慈善募捐，是用户自愿多付、用来把价格压给所有人的赞助。Donating grants no extra privileges: no bonus quota, no queue priority, no unlocked features. The pool balance and full ledger are visible in the console at any time. Not a charity appeal — it is users voluntarily paying a little extra, spent on keeping the price low for everyone.

不会。请求内容仅用于本次推理，不用于训练、不对外共享。企业版可提供数据不出境与完整私有化部署。No. Request content is used only to serve that request — never for training, never shared. An enterprise tier offers data residency and fully private deployment.