Offers
Offers and discounts
Discounts, intro prices, boosted allowances and standing off-peak rates, each quoted from the vendor page it was read on. A campaign ends without the plan price changing, so it is listed here instead of in the plan table.
Campaigns and limited-time offers
Discounts, intro prices, boosted allowances and standing off-peak rates, each quoted from the vendor page it was read on. A campaign ends without the plan price changing, so it is listed here instead of in the plan table.
- DiscountOpenCodeLimited time
Gemini 4 Argon: 50% off list, already applied in the price shown.
Vendor wordingGemini 4 Argon (50% off): $4.00 $2.00
source - Extra allowanceCommand CodeLimited time
deepseek-v4.1-flash: boosted allowance of $10 on Go while capacity lasts.
Go $10 · GOAT $80 · Pro $90
Vendor wordingDEAL deepseek-v4.1-flash boosted usage: $10 Go, $80 GOAT, $90 Pro.
source - Extra allowanceCommand CodeLimited time
glm-5.3-flash: boosted allowance of $10 on Go while capacity lasts.
Go $10 · GOAT $80 · Pro $90
Vendor wordingDEAL glm-5.3-flash boosted usage: $10 Go, $80 GOAT, $90 Pro. while capacity lasts
source - Extra allowanceCommand CodeLimited time
ling-3.1-flash: boosted allowance of $100 on GOAT while capacity lasts.
GOAT $100 · Pro $110
Vendor wordingDEAL ling-3.1-flash boosted usage: $100 GOAT, $110 Pro.
source - Extra allowanceCommand CodeLimited time
minimax-m3: 2× usage on Go while capacity lasts.
Vendor wordingDEAL minimax-m3 2× usage. Every credit goes 2× further.
source - Intro priceOpenDesignLimited time
First month $8 instead of $10.
Go $8 · Plus $16 · Pro $70 · Max $120
Vendor wordingdata-intro-price="8" data-regular-price="10"
source - Discount火山方舟 VolcengineLimited timeFree until 2026-12-14
kimi-k2.8-preview: limited-time 40% off, so the same allowance buys more tokens.
Vendor wordingkimi-k2.8-preview | 进行中 | 新模型上线限时活动，活动期间，Coding Plan 中 Kimi-K2.8-Preview 的可用量，与 Agent Plan 6 折抵扣活动期间相当。
source - Discount火山方舟 VolcengineLimited timeFree until 2026-10-25
kimi-k3: limited-time 50% off, so the same allowance buys more tokens.
Vendor wordingkimi-k3 | 进行中 | 活动期间，Coding Plan 中 Kimi-K3 的可用量，与 Agent Plan 5 折抵扣活动期间相当。
source - Discount火山方舟 VolcengineLimited timeFree until 2026-11-09
kimi-k3.1-pro: limited-time 50% off, so the same allowance buys more tokens.
Vendor wordingkimi-k3.1-pro | 进行中 | 新模型上线限时活动，活动期间，Coding Plan 中 Kimi-K3.1-Pro 的可用量，与 Agent Plan 5 折抵扣活动期间相当。
source - Discount火山方舟 VolcengineLimited timeFree until 2026-12-30
deepseek-v4.1-flash: limited-time 50% off, so the same allowance buys more tokens.
Vendor wordingdeepseek-v4.1-flash | 进行中 | 新模型上线活动，活动期间模型抵扣系数在现有抵扣系数基础上享 5 折优惠，可使用配额为原用量的 200%。
source - Discount火山方舟 VolcengineLimited timeFree until 2026-12-30
deepseek-v4.1-flash-economy: limited-time 50% off, so the same allowance buys more tokens.
Vendor wordingdeepseek-v4.1-flash-economy | 进行中 | 新模型上线活动，活动期间模型抵扣系数在现有抵扣系数基础上享 5 折优惠，可使用配额为原用量的 200%。
source - Intro price火山方舟 VolcengineLimited time
First 2 months ¥9.9 instead of ¥40.
Coding Plan Lite ¥9.9 · Coding Plan Pro ¥49.9
Vendor wording2026年6月8日至2026年11月8日活动期间内，所有用户购买 Coding Plan Lite、Pro 套餐，最多可享首两个月 2.5 折优惠，第三个月起恢复原价。**名额有限，先到先得**；优惠资格在新购、续费、升级场景间共享，使用后不因升档或后续退订等操作重新获得。
source - Intro price阿里云百炼 Alibaba Model StudioLimited time
First month ¥39.9 instead of ¥200.
Vendor wording- <strong>新客首月特惠：</strong>首次订阅 Pro 套餐可享首月 ¥39.90（官网目录价 ¥200/月），后续按 ¥200/月 续费，具体以下单页为准。
source - Free trialCerebras CodeLimited time
A limited free trial runs GLM-4.7 with capped tokens and requests.
Vendor wordingFree Trial Limited Free Credits GLM 4.
source - Free tierGitHub CopilotLimited time
Copilot Free and Student include a small AI-credit allowance, in-product only.
Vendor wordingOn Copilot Free and Copilot Student plans, access to models is available through auto model selection only.
source - Discount百度千帆 QianfanLimited timeFree until 2026-11-30
Off-peak calls (22:00-08:00) on 3 named models cost 80% less until 2026-11-30.
Vendor wording活动期间，Token Plan个人版 积分制 用户每日 22:00 - 次日 8:00 调用指定模型， 低至 2 折 。
source - Discount月之暗面 KimiStanding rule
Annual billing is about 20% cheaper: Plus ¥79/month instead of ¥99.
Vendor wordingAnnually · Save up to ¥3,360 · Plus ¥ 79 / month ¥99 · Billed annually ¥948
source - Intro priceMiniMaxLimited time
First month $11 instead of $22.
M Plan Go $11 · M Plan Explore $27.5 · M Plan Build $66
Vendor wordingM Plan: First month 50% off, then full price.
source - Free tierAnthropic ClaudeLimited time
Claude Free is a $0 tier for chat on web, desktop and mobile, without Codex-style usage.
Vendor wordingFree Try Claude $0 Free for everyone
source - DiscountAnthropic ClaudeStanding rule
Paying yearly brings Pro to $17/month, about 15% below the monthly price.
Vendor wordingPer month with annual subscription discount ( $200 billed up front). $20 if billed monthly.
source - Student offerAnthropic ClaudeLimited time
Universities can buy discounted access for every member; the percentage is not published.
Vendor wordingComprehensive access for all university members at discounted rates
source - Free tierOpenAI ChatGPTLimited time
ChatGPT Free includes Codex on quick tasks, with GPT-6 Luna at Standard speed.
Vendor wordingFree Explore Codex capabilities on quick coding tasks. $0 /month
source - DiscountOpenAI ChatGPTStanding rule
Business seats are $20/user billed yearly versus $25 monthly, about 20% less.
Vendor wordingBusiness Bring Codex into your startup or growing business. $20 / user / month
source - Free tierCursorLimited time
Cursor Free is a $0 tier with limited agent and chat requests, in-product only.
Vendor wordingFree | $0 | /month | Get started with: | Limited | AI usage
source
Standing pricing rules
List unit price with the offers that apply today folded in: a discount lowers it, a boosted allowance divides it. The list price stays visible in the plan table.
- Off-peak rateOpenCodeLimited time
DeepSeek V4.1 Flash is priced per time of day: the off-peak row is half the peak rate, and both are listed.
Vendor wordingDeepSeek V4.1 Flash (Off-Peak): $0.15 / $0.60
source - Off-peak rateOpenCodeLimited time
DeepSeek V4 Pro is priced per time of day: the off-peak row is half the peak rate, and both are listed.
Vendor wordingDeepSeek V4 Pro (Off-Peak): $0.66 / $1.98
source - Off-peak rateOpenDesignLimited time
A week-long campaign bills DeepSeek V4.1 Flash at off-peak rates.
Vendor wordingOpenDesign Motion Week · DS off-peak rates. Opus 5.5-level motion." data-astro-cid-c2p52qye>
source - Off-peak rateZ.aiStanding rule
Off-peak usage is charged at 50% of the standard credit rate.
Vendor wording**During off-peak hours, model usage is charged at 50% of the standard credit rate**.
source
Read the numbers like this
- A plan is not a price per token. The same $20 buys 1.5B tokens of a cheap open model or 40M tokens of a frontier model, and several plans grant a different allowance per model.
- Request-based plans are converted with a stated tokens-per-request assumption, because a request count is not a token count. Treat those rows as an estimate and check your own task size.
- Credits are converted with the vendor's own formula (credits = weighted tokens / divisor, peak/off-peak multipliers applied), so the number is exact for that model but moves with time-of-day.
- Claude, ChatGPT, Cursor, Kimi and MiniMax publish no convertible allowance at all. They stay in the table, sorted last, with their price — an honest gap beats an invented number.
FAQ
Why do some rows show a token count and others say not quantified?
Because plans do not sell tokens. Some sell a dollar allowance (OpenCode, Command Code, OpenDesign), some a token volume (Synthetic, Cerebras, Baidu), some vendor credits with per-model multipliers (Z.ai, Volcengine Agent Plan), some a request count (Volcengine, Alibaba), and the biggest names sell an unquantified "usage" (Claude, ChatGPT, Cursor, Kimi, MiniMax). The Allowance column says which, so an inferred number is never mistaken for a published one.
Why not just compare the price per million tokens?
Input, cached read, cached write and output are priced separately, and their ratios differ by an order of magnitude between providers. A single blended figure at stated assumptions is the only number that compares plans honestly.
I only care about one model. What do I do?
Pick the model family first (DeepSeek, GLM, Claude, Qwen...). The page then lists every vendor that resells that family, what each plan costs, how many tokens the plan buys at your cache hit rate, and the resulting blended unit price.
How accurate is the token estimate?
Request counts are the one estimate on the page: they are multiplied by a stated tokens-per-request figure that you can adjust. Every other conversion uses a number the vendor publishes, and every row links to its source page so you can check it.
Where does this data come from?
Unit prices come from LiteLLM and OpenRouter; subscription prices and allowances are parsed from each vendor's own plan page (or declared with an anchor guard when the page only renders prices in the browser). The verified date is on every row — prices move, so re-check before committing to an annual plan.