The cheap open models are out there. Actually using them is the annoying part.

廉价的开源模型随处可见，但真正使用它们却很麻烦。

Open-weight models quietly got good this year — good enough that for most real engineering work I genuinely can’t tell them apart from the flagships. And they’re a fraction of the price. On paper, everyone should already be using them. In practice, they don’t, and it’s not because the models are bad. It’s because actually using cheap inference is a hassle. 今年，开源权重模型悄然变得强大起来——强大到在大多数实际工程工作中，我真的无法将它们与旗舰模型区分开来。而且它们的价格仅为后者的一小部分。理论上，每个人都应该已经在使用它们了。但在实践中，人们并没有这样做，这并不是因为模型不好，而是因为使用廉价推理服务实在太麻烦了。

Between finding a provider, wiring up a gateway, managing keys, and figuring out billing, there’s enough friction that most people just keep paying OpenAI out of inertia. I know, because I spent a while on the annoying side of it. The models are cheap. The plumbing is the problem. 在寻找服务商、配置网关、管理密钥和处理账单之间，存在着足够的阻力，导致大多数人出于惯性继续向 OpenAI 付费。我深有体会，因为我曾在那令人烦恼的一端折腾了很久。模型本身很便宜，但底层的“管道”工程才是问题所在。

Here’s the thing I kept running into: getting low-cost inference for open models is very doable, but the path from “cheap compute exists” to “I can just make an API call and pay for it like a normal person” is full of small headaches. Provider accounts. Wallets. Prepaid ledgers. No clean way to just put in a card and get an API key that works with the tools you already use. None of that is hard, exactly. It’s just enough papercuts that it isn’t worth it for most developers — so the cheap models sit there unused while people overpay for the convenient ones. That gap is the whole reason I built something. 我不断遇到的问题是：为开源模型获取低成本推理服务完全可行，但从“存在廉价算力”到“我可以像正常人一样发起 API 调用并付费”的过程充满了琐碎的麻烦。服务商账户、钱包、预付账单……没有一种简单直接的方式能让你绑定信用卡并获得一个能直接用于现有工具的 API 密钥。这些事情本身并不难，但足以构成“千刀万剐”般的阻碍，让大多数开发者觉得不值得——于是廉价模型被闲置，而人们却在为便捷性支付高昂的溢价。这种差距正是促使我开发这个产品的原因。

So I built the easy part and hid the hard part. I took the annoying plumbing — the inference sourcing, the gateway, the metering, the key management — and put a boring, familiar surface on top of it: It’s OpenAI-compatible, so you change a base URL and keep your code. You pay with a card or USDT, top up a prepaid balance, and that’s it. No wallet, no subscription, no crypto rabbit hole unless you want one. Every key has a hard budget cap, so a runaway loop stops instead of surprising you. 所以我构建了简单易用的部分，并隐藏了复杂的部分。我处理了那些令人烦恼的底层工作——推理源接入、网关、计量、密钥管理——并在其上覆盖了一个枯燥且熟悉的界面：它兼容 OpenAI，因此你只需更改基础 URL 即可保留原有代码。你可以使用信用卡或 USDT 充值余额，仅此而已。没有钱包、没有订阅、没有你不需要的加密货币陷阱。每个密钥都有严格的预算上限，因此失控的循环会及时停止，而不会给你带来意外的账单。

I called it Khidi — ხიდი, “bridge” in Georgian. The name is the whole idea: a bridge from the tools you already use to models that cost a tenth as much. Full disclosure up front: I run it (khidi.ai), so read this as a founder explaining what he built, not a neutral review. The pitch is simple — the cheap models were always available; I just made them as easy to use and pay for as the expensive ones. 我把它命名为 Khidi（格鲁吉亚语中意为“桥梁”）。这个名字概括了核心理念：一座连接你现有工具与成本仅为十分之一的模型的桥梁。事先声明：我运营着这个平台 (khidi.ai)，所以请将此文视为创始人对自己产品的介绍，而非中立的测评。我的核心卖点很简单——廉价模型一直都在，我只是让它们变得像昂贵模型一样易于使用和付费。

What it costs

成本分析

A typical coding-agent month is roughly 50M input + 10M output tokens. Same requests, different providers: 一个典型的编码智能体每月大约消耗 5000 万输入 Token 和 1000 万输出 Token。同样的请求，不同服务商的对比：

Provider (model)	Price /1M (in · out)	Monthly bill
OpenAI (GPT-5.5)	$5.00 · $30.00	$550.00
Anthropic (Claude Opus 4.8)	$5.00 · $25.00	$500.00
Moonshot (Kimi K2.6, direct)	$0.95 · $4.00	$87.50
Kimi K2.6, at ~half vendor price	$0.50 · $2.00	$45.00

And this isn’t cheap-because-worse. On contamination-resistant benchmarks — resolving real GitHub issues, using tools — the open flagships hold their own: Kimi K2.6 scores 58.6 on SWE-Bench Pro (ahead of GPT-5.4’s 57.7 and Claude Opus 4.6’s 53.4), and 92.5 on DeepSearchQA (ahead of GPT-5.4’s 78.6). Vendor-reported for the exact versions, spring 2026. 这并不是因为便宜所以性能差。在抗污染基准测试中（如解决真实的 GitHub 问题、使用工具等），开源旗舰模型表现出色：Kimi K2.6 在 SWE-Bench Pro 上得分为 58.6（领先于 GPT-5.4 的 57.7 和 Claude Opus 4.6 的 53.4），在 DeepSearchQA 上得分为 92.5（领先于 GPT-5.4 的 78.6）。以上数据为 2026 年春季各厂商针对特定版本的报告。

How you use it

如何使用

Keep the OpenAI SDK. Change one line: 保留 OpenAI SDK，只需修改一行代码：

from openai import OpenAI
client = OpenAI(
    base_url="https://api.khidi.ai/v1",
    api_key="sk-...",
)
client.chat.completions.create(
    model="kimi-k2.6",
    messages=[{"role": "user", "content": "hello"}],
)

Streaming, tool calling, long context all work, because the interface is identical. Cursor, LangChain, LibreChat, n8n — same story. It works with Claude Code too. Claude Code speaks Anthropic’s format rather than OpenAI’s, but the gateway translates between them, so you can run Claude Code’s whole workflow on an open model: 流式传输、工具调用、长上下文功能均可正常使用，因为接口完全一致。Cursor、LangChain、LibreChat、n8n 等工具也是如此。它甚至支持 Claude Code。Claude Code 使用的是 Anthropic 的格式而非 OpenAI 的格式，但网关会在两者之间进行转换，因此你可以在开源模型上运行 Claude Code 的完整工作流：

export ANTHROPIC_BASE_URL="https://api.khidi.ai"
export ANTHROPIC_AUTH_TOKEN="sk-..."
claude --model kimi-k2.6

Same terminal workflow, a fraction of the cost. Basic usage is solid; some Claude-specific features can be hit or miss through translation, so test your exact flow. 同样的终端工作流，成本却只有一小部分。基础使用非常稳定；由于翻译转换的原因，某些 Claude 特有的功能可能表现不稳定，因此请务必测试你的具体工作流。

What I won’t oversell

我不会过度吹嘘的部分

The newest closed flagship is still ahead on the hardest problems — by a little, at a lot more money. Frontier research? Pay for the frontier. Normal engineering? You’re overpaying. Latency and reliability vary more with any hosted open-model service than with OpenAI’s own stack. Streaming feels fine; non-streaming can be slower. Test your workload. Open-model line-ups shift. Don’t hardcode assumptions about what’s available. 最新的闭源旗舰模型在处理最困难的问题时仍然领先——虽然领先幅度很小，但价格却高得多。前沿研究？请为前沿付费。普通工程？你付出的钱太多了。与 OpenAI 自家的技术栈相比，任何托管的开源模型服务的延迟和可靠性波动都更大。流式传输感觉不错，非流式传输可能会慢一些。请测试你的工作负载。开源模型阵容在不断变化，不要对可用模型做出硬编码的假设。

Try it on one project

在一个项目中尝试一下

The models were never the blocker — the friction was. If cheap, capable inference behind a card-and-a-base-URL sounds useful, point one project at it and compare the output honestly. Worst case you confirm you really need the flagship. Best case you cut your biggest variable cost by an order of magnitude, with none of the setup that usually makes people not bother. You can try it at khidi.ai — there’s a free trial budget on sign-up, no card needed to start. 模型从来不是阻碍，阻碍的是繁琐的流程。如果“通过信用卡和基础 URL 即可获得廉价且强大的推理服务”听起来很有用，那就拿一个项目试一试，并诚实地对比输出结果。最坏的情况是你确认自己确实需要旗舰模型；最好的情况是你将最大的可变成本降低了一个数量级，且无需经历那些通常让人望而却步的繁琐设置。你可以在 khidi.ai 尝试——注册即送免费试用额度，无需绑定信用卡即可开始。