This file holds the full pricing guidance, the mandatory cost-estimation disclaimer (in both Chinese and English), and the usage/billing console reference. SKILL.md keeps only a one-line pointer; whenever you produce a cost-related answer, you must read and apply this file.
- Default pricing reference: pricing.md — Structural overview only.
qianwen models info --format json first (returns structured pricing tiers).
Fall back to the official pricing page
only if CLI is unavailable. Never invent a number.
Cost = Tokens ÷ 1,000,000 × Unit price. 1K Chinese chars ≈ 1,200–1,500 tokens.qianwen usage free-tier --format json.
When the user asks about actual usage, spending history, or billing details — direct them to the appropriate console page (these are NOT accessible via API; the user must open them in a browser):
| Question | Console Page | |---------------------------------------------------------|--------------| | "How much have I used?" / "Show my usage" | Usage Analytics | | "Show my bill" / "How much did I spend?" (pay-as-you-go)| Pay-as-you-go Billing | | "Show my Token Plan bill" / "Token Plan 团队版 usage" | Token Plan Subscription |
Important: This skill can estimate costs based on published unit prices, but cannot query the user's
actual account balance, historical spending, or remaining quota. For real-time account data, always direct
the user to the console pages above.>
NEVER fabricate, guess, or construct usage/billing/console URLs. Only provide the exact links listed in
this skill. If a URL is not listed here, do not invent one.
🚨 CRITICAL — NO EXCEPTIONS: NEVER fabricate, invent, or guess any price figure. If you do not have
a confirmed price from CLI (qianwen models info),pricing.md, or the official pricing page, you
MUST NOT output any number. Instead, direct the user to the
official pricing page.
Outputting a made-up price is a critical failure — worse than saying "I don't know."
When responding to any cost-related query — including but not limited to price evaluation, usage estimation, budget forecasting, or cost comparison — you MUST append a professional disclaimer. This applies regardless of language or response format.
⚠️ 费用说明：以上费用为基于官方公示单价的预估价格，仅供参考。实际费用受 Token
消耗量、上下文长度阶梯定价、Batch/缓存折扣及计费策略调整等因素影响，请以QianWen控制台的实际账单为准：按量付费账单 | Token Plan 团队版订阅 | 用量分析。部分模型可能提供限时免费额度，但免费额度的可用性、额度量及有效期随时可能调整，请在控制台确认您的账户是否仍有剩余额度，切勿假设本次调用免费。最新定价详见 模型定价页。
⚠️ Pricing Notice: The cost figures above are estimates calculated from officially published unit prices and
are provided for reference only. Actual charges depend on token consumption, tiered context-length pricing,
Batch/cache discounts, and billing policy updates. Some models may offer a time-limited free quota, but
quota availability, amounts, and validity periods are subject to change — do not assume this call is free. Please
verify your remaining quota in
the QianWen console and refer to your actual
bill for definitive costs: Pay-as-you-go Billing |
Token Plan 团队版 Subscription |
Usage Analytics.
See Model Pricing for
the latest rates.
- The disclaimer must appear at the end of every cost-related response, clearly separated from the main content.