If you code with AI all day — agents, documentation, batch jobs — the bill adds up fast. Pay-as-you-go API pricing is wonderfully flexible right up until you see the invoice. For most of my day-to-day work, I’ve switched to subscription-based coding plans, mostly from Chinese providers, which trade a little flexibility for a much friendlier price.
A quick bit of context on why I care about this. I split my time between Hong Kong and Shenzhen, which turns out to be a near-ideal setup. In Hong Kong I pay just HK$199 a month (about US$25) for symmetric 5 Gbps fibre — that’s what most of my AI-agent web research runs on, since all that crawling and fetching eats bandwidth both ways. Across the border in Shenzhen, I pay ¥159 a month for 2500/150 Mbps, plus something the HK side can’t easily give me: frictionless access to the local Chinese model providers, where the Alipay/WeChat payments and local endpoints that trip up overseas users just work. That combination is how I keep costs near zero while building odw.ai and the suite of ten products we’re launching — in the open, with the source shared for anyone who wants it.
A site that compares them all
Comparing these plans by hand is miserable — every provider prices differently, and the tiers rarely line up. I found this site recently and it does the tedious work for you:
https://z4crk6mg95.coze.site/index.html
It’s in Chinese, so translate it if needed, but the numbers that matter — prices, quotas, models — read fine either way. Everything’s in one table: monthly/quarterly/yearly pricing, the 5-hour and weekly quotas, the models each tier unlocks, and a rough star rating. Coverage is broad: Zhipu (GLM), MiniMax, iFlytek Spark, ByteDance’s Volcano Ark, Kimi, Xiaomi MiMo, Alibaba Bailian (Qwen), and DeepSeek, plus Codex and OpenCode for comparison.
One caveat: the table normalises everything into comparable units, so many figures are best-effort estimates rather than official numbers. Treat it as a starting point to build a shortlist, then confirm on the provider’s own page — and note the activation links appear to route through a referral domain.
Why coding plans, and when
The appeal is simple: used well, they’re far cheaper than metered API access. The trade-offs are two. You’re limited by usage pattern — you can’t blitz your whole allowance at once, since caps usually apply to a rolling window (most often any 5-hour period). And you’re limited by models — cheaper tiers lock you out of the strongest models or burn quota faster when you use them.
So they’re my go-to for anything non-critical and non-urgent. If a task can wait or be chunked, it’s a great fit; if I need a guaranteed answer right now, I pay for on-demand API and move on. The 5-hour window sounds restrictive but rarely is, because agents run unattended: queue a backlog and drip-feed it, batch the heavy jobs overnight, and use a cheap model for the boring 80% while saving the pricey one for the parts that need it.
Can you use them outside China?
Mostly yes — but several providers run two platforms: a mainland version (CNY, Alipay/WeChat) and an international one (USD, foreign cards, a different endpoint). The comparison site reflects this, listing domestic and “international” versions separately.
The most foreigner-friendly are Zhipu/GLM (via its global site z.ai) and MiniMax (USD pricing, dedicated international endpoint) — both built to work from abroad. Just sign up for the right version and point your tools at the international endpoint, or they’ll silently fail. DeepSeek is pay-as-you-go and works fine abroad; the usual snag is your own bank blocking a China merchant, which a quick call fixes. The more domestic players — iFlytek, Volcano Ark, Xiaomi MiMo, Bailian — may want a Chinese phone number or ID and a Chinese-only console.
Two things regardless of provider: payment is the main friction point (the USD platforms sidestep it), and some employers or jurisdictions restrict Chinese AI tools over data-residency rules — so able to access isn’t the same as allowed to use.
The bottom line
Coding plans won’t replace on-demand access for urgent, critical work, and truly uncapped token plans are still — let’s be honest — reserved for the rich. 😃 But for the growing pile of work that’s important yet not urgent, they’re an excellent, cheap fallback. Work out your usage pattern, pick a plan whose quotas and models fit it, and let your agents handle the scheduling. It’s the same frugal approach that lets us build odw.ai and ship in the open — and the comparison site above is the best place to start.
Leave a Comment