Tony Nguyen · research note · 2026-07-30
The subscription is cheap. The quota math is not.
Which paid subscription gives a developer in mainland China a large interactive coding-agent allowance with a model at least around GLM-5.2? Short answer: Baidu Qianfan Token Plan Personal — the only plan in this survey with a published monthly token quota, from ≈ $0.064 per 1M tokens (currently displayed promo). Most others sell credits, prompts, requests or dollar caps — and those cannot be compared with tokens.
Decision tool
16 candidates — one table, one graph
Only tiers with a published monthly token quota sit on the numeric axis — currently just Baidu Qianfan. Everything else stays in the "not token-priced" band.
MiMo and Tencent credits converted with the official per-1M cache-miss input coefficient (mimo-v2.5: 100 credits; GLM-5.2 on Tencent: 154 credits). Not comparable across baselines or with published tokens.
The "not token-priced" band: plans billed in credits, prompts, requests, dollar caps or app credits — x position means nothing here.
The table is wide — scroll it sideways; the first column stays put.
| Provider / plan | Recurring price / mo | Quota unit | Reset / window | Integration / API | Availability | Confidence / note |
|---|---|---|---|---|---|---|
| Mainland China and global token plans | ||||||
| Baidu QianfanToken Plan Personal | ≈ $1.46–88.63 (¥9.9–600; promo ¥4.9–299.9 ≈ $0.72–44.30) | tokens / month (shared across models) | monthly | subscription · OpenAI + Anthropic-compatible endpoint · dedicated key · interactive tools only | mainland China — account with a mainland number and identity verification | promo has no stated expiry — verify at checkout |
| VolcanoArk Coding Plan | from ¥9.9 (~$1.46) promo start · ongoing prices not public | not public — 5-hour / weekly / monthly quota | 5h / week / month — verify at checkout | subscription · Claude Code, Codex CLI, OpenCode, Hermes Agent, TRAE, Cursor (campaign) | mainland China | no public ongoing table — promo start only, verify at checkout |
| ZhipuGLM Coding Plan | ≈ $7.24–69.28 / mo (¥49 / 149 / 469) | prompts / 5h (≈80–1,600) · 1 prompt ≈ 15–20 calls | 5-hour window + weekly (400–8,000) | subscription · OpenAI + Anthropic protocols · Claude Code, Cline, OpenCode, Cursor, Hermes… | mainland China | 3x peak, 2x off-peak coefficient; temporary 1x off-peak promo through end of September |
| XiaomiMiMo Token Plan | ≈ $5.76–97.35 / mo (¥39 / 99 / 329 / 659) · annual ≈ −12% | credits (4.1–82B) · official per-1M coefficients — not raw tokens | monthly · 0.8x coefficient 00:00–08:00 UTC+8 | subscription · OpenAI/Anthropic-compatible · OpenCode, OpenClaw, Claude Code | mainland + Singapore and Europe endpoints | official per-1M coefficients exist — credits are still not raw tokens |
| TencentToken Plan Personal Edition | $7–103 / mo (1,000–15,900 credits) | token-weighted credits · official per-1M coefficients — not raw tokens | subscription month · no rollover | subscription · sk-tp-… key · OpenAI + Anthropic-compatible · Hermes, OpenCode, Claude Code, Cursor, Cline, Codex CLI | Singapore region (international, English docs) | official per-1M coefficients exist — credits are still not raw tokens |
| KimiKimi Code | from ≈ $7.24 / mo (CN ¥49–699 ≈ $7.24–103.25; international $19–199) | 1x–30x multiplier · rolling 5-hour window ≈ 300–1,200 requests | quota refreshes every 7 days | subscription · Kimi web / CLI / VS Code + third parties · overage with a monthly cap | international + CN — region-dependent pricing | region-dependent — verify at checkout |
| MiniMaxToken Plan | ≈ $7.24–69.28 / mo (¥49 / 119 / 469) | fixed 5-hour + weekly window | 5h + weekly | subscription · subscription key · platform models | mainland China — verify availability | quota less public — verify model, limit and coefficient |
| OpenCodeGo | $10 / mo ($5 first month) | dollar caps: $12 / 5h · $30 / week · $60 / month | 5h / weekly / monthly caps | subscription · OpenAI-compatible endpoint · official OpenCode provider | global (US/EU/SG hosting) — test mainland latency and payment | $5 first month is promo; $10 recurring |
| Western and global subscriptions | ||||||
| OpenAIChatGPT + Codex | $20–200 / mo (Plus $20 · Pro 5x $100 · Pro 20x $200) | dynamic limits / credits — no fixed token quota | dynamic · shared across ChatGPT and Codex | subscription (Codex web / CLI / IDE / iOS) · pay-as-you-go API is separate | supported countries · mainland China is not listed | API key ≠ subscription credit · mainland officially unsupported |
| AnthropicClaude Pro / Max + Claude Code | $20–200 / mo (Pro $20, $17 annual effective · Max 5x $100 · Max 20x $200) | rolling 5-hour window + weekly limits · no message count | rolling 5h + weekly | subscription · Claude Code in terminal and IDEs · ANTHROPIC_API_KEY switches to API billing | supported locations · mainland China is not listed | not a reusable API key · usage credits after quota = API pricing |
| GitHubCopilot Pro / Pro+ / Max | $10–100 / mo (Pro $10 · Pro+ $39 · Max $100) | AI credits 1,500 / 7,000 / 20,000 / mo (1 = $0.01) · completions unlimited | monthly at 00:00 UTC · no rollover | subscription · VS Code, JetBrains, Neovim, Zed, CLI · delegates to Claude and Codex | global (GitHub regions) | chat/agents/CLI consume credits — completions do not |
| CursorPro / Pro Plus / Ultra | $20–200 / mo (Pro $20 · Plus $60 · Ultra $200; included usage $20 / $70 / $400) | included dollar usage · cloud agents at API pricing | monthly | editor subscription · integrates inside Cursor · not an external provider | global | credits do not work outside Cursor (Cline/OpenCode/aider) |
| ReplitCore / Pro | $25–100 / mo ($20 / $95 annual) · $25 / $100 app credits | app / platform credits · Pro: up to 10 parallel agents | monthly | hosted environment · not a portable API key | global (hosted) | usage depends on Agent mode and effort |
| xAISuperGrok / X Premium+ + Grok Build | $40 / mo ($395 / year) | one shared weekly pool across Grok products — no public quota | weekly pool | X subscription · OAuth into OpenCode, Kilo, OpenClaw, Hermes · Grok Build beta · xAI API separate | global (X regions) | the pool is not unlimited — validate usage in your own account |
| ZedPersonal / Pro (editor) | no public monthly seat price · Pro includes $5 of hosted tokens (+ API list price +10%) | $5 hosted tokens · free 2,000 edit predictions | — | editor · own API keys or external agents (Claude Agent, Codex CLI) | global | pricing exposes no stable monthly seat price — I am not inventing one |
| GoogleGemini CLI → Antigravity CLI | verify at checkout · Google AI Pro/Ultra is a separate product | transition — limits are not stable | — | consumer Gemini CLI ended 2026-06-18 · Antigravity CLI · enterprise/API paths remain | global (Google AI plan regions) | I do not present the old Gemini CLI subscription path as current |
Method & sources
Official pages and docs, nothing else.
Data checked against official pages and docs on 2026-07-30. USD conversions are approximate, at the historical indicative rate 1 USD = 6.77 CNY — not a card rate. "Model-equivalent tokens" use only the official credit coefficients (MiMo, Tencent); no averages, no guesses. Every plan measures consumption differently — none is "unlimited".
I have not benchmarked model quality — the numbers above are prices and quotas, not performance. For independent model-quality and price benchmarking: Artificial Analysis
Each plan's official sources are in the selected-dot detail.
Historical indicative rate 1 USD = 6.77 CNY, last updated 2026-07-30: exchangerates.org.uk