The Kimi Code CLI is free, and access to the models behind it is sold in three ways: a Kimi membership starting at $19 per month, an Extra Usage wallet that takes over when the membership quota runs out, and the Kimi pay-as-you-go Open Platform API, priced at $3 per million input tokens and $15 per million output tokens for K3. The membership quota is not published, so the choice among the three depends on usage. The calculation below shows where the break-even point falls. Prices read from kimi.com and platform.kimi.ai on October 1, 2026.
To learn what Kimi Code is and how it differs from other tools, see the English page Kimi Code vs Claude Code; to switch clients, memberships, or models, see Kimi Code alternatives. The English original of this page is Kimi Code pricing.
Membership tiers
| Tier | Monthly billing | Annual billing | Kimi Code and K3 | K3 1M context, HighSpeed |
|---|---|---|---|---|
| Plus | $19 | $15 per month ($180 per year) | Included | Not included |
| Pro | $39 | $31 per month ($372 per year) | Included | Included |
| Max | $99 | $79 per month ($948 per year) | Included | Included |
| Ultra | $199 | $159 per month ($1,908 per year) | Included | Included |
Prices are from kimi.com's membership page (prices are rendered in the browser, not in the page source). The two columns on the right are from Kimi's membership documentation. Free accounts and the Go tier do not include Kimi Code quota. Kimi recently renamed its tiers while saying “prices unchanged”; existing plans keep their old names and rules until you switch. All amounts are in US dollars; the actual amount charged in Korean won depends on the exchange rate and the card issuer at the time of payment.
How the quota works
- Everything draws from one pool. Requests from the CLI, VS Code, the desktop app, and third-party tools all count toward the same membership quota, shared by all signed-in devices and API keys.
- A rolling five-hour window limits bursts and recovers automatically. New members no longer have a weekly limit; legacy plans still reset every seven days from the subscription date, with no rollover.
- A total monthly quota is shared with Kimi on the web; when it runs out, Kimi Code stops until reset or upgrade.
- No figures are published for any of the three. Neither token counts nor request counts are available. Check remaining quota in the Kimi Code Console or in the CLI with
/usage.
Extra Usage: the wallet beyond your quota
When the membership quota runs out, Extra Usage continues requests from a prepaid balance. The rules in the same documentation are as follows:
- Only subscribers can enable it, and Kimi on the web and Kimi Code share one balance.
- Billed in yuan according to actual usage, at rates Kimi describes as close to Open Platform API prices. Kimi itself also says upgrading the subscription is usually better value for heavy use.
- It is deducted last, after the subscription quota, so tasks keep running instead of failing. Without a monthly spending limit set in settings, there is no cap.
- Top-ups start at ¥25, with a daily maximum of 10 top-ups and ¥3,000, and a balance cap of ¥10,000. The balance does not expire and remains if the subscription lapses (but you cannot top up while it is lapsed); it is generally non-refundable.
Pay-as-you-go API pricing per token
| Model ID | Input (cache miss) | Input (cache hit) | Output | Context |
|---|---|---|---|---|
kimi-k3 — 캐시 쓰기 $3.00(5분 TTL) 또는 $6.00(1시간) | $3.00 | $0.30 | $15.00 | 1,048,576 tokens |
kimi-k2.7-code | $0.95 | $0.19 | $4.00 | 262,144 tokens |
kimi-k2.7-code-highspeed | $1.90 | $0.38 | $8.00 | 262,144 tokens |
Per million tokens, before tax, from platform.kimi.ai. The API base URL is https://api.moonshot.ai/v1 and accepts requests in OpenAI and Anthropic formats. This is a separate product from the membership, with its own account and key; its model IDs (kimi-k3, kimi-k2.7-code) also differ from the membership IDs (kimi-for-coding, k3). Membership cannot pay for API calls, and API balance does not increase membership quota.
Membership or pay-as-you-go: the break-even point
The following is token arithmetic, not measured task cost. One session sends 200,000 uncached input tokens and receives 12,000 output tokens.
| Route | One session | Number of sessions equivalent to Plus ($19) | Who bills you |
|---|---|---|---|
kimi-k3, pay-as-you-go | $0.78 | about 24 | Kimi Open Platform |
kimi-k3, 80% of input cache hit | $0.35 | about 55 | Kimi Open Platform |
kimi-k2.7-code, pay-as-you-go | $0.24 | about 80 | Kimi Open Platform |
| Claude Haiku 4.5 through Kunavo | $0.18 | about 104 | Kunavo |
| Claude Sonnet 5 through Kunavo | $0.36 | about 52 | Kunavo |
Read this as a threshold. If you run fewer sessions of this kind with K3 per month than the number in the third column, the pay-as-you-go API costs less than Plus. If you run more, Plus is likely cheaper, until the five-hour window or monthly total quota stops you; this is the part Kimi does not quantify. The cached row does not include the initial cache-write cost ($3 or $6 per million tokens depending on cache lifetime). “Lowest unit price” and “cheapest way to finish the task” are different things. A model that needs three retries may cost more than a pricier model that finishes in one.
Kunavo’s two rows are the real-time catalog rates for Claude models, and Kimi Code can connect to them using the openai provider type. Kunavo does not sell Kimi models. Catalog amounts are the billing floor, not the ceiling. When the upstream provider reports a cost, the amount charged is the greater of the catalog amount and “upstream cost × applicable margin.” Kunavo bills by token from a prepaid balance; the minimum top-up is $10, and there is no subscription (Billing guide). Payments are handled by Stripe; in Korea, cards (Visa, Mastercard, American Express, JCB, UnionPay), Apple Pay, Google Pay, and Link are supported, and when checkout is displayed in KRW, Kakao Pay, Naver Pay, PAYCO, Samsung Pay, and domestic cards with international payments disabled are also available. These methods top up your Kunavo balance; the KRW exchange rate includes a 2–4% conversion fee paid by the purchaser, which does not apply when paying in dollars (Stripe Adaptive Pricing documentation, checked on 2026-10-03). The provider configuration block is on Kunavo’s Kimi Code configuration page. No one has yet run Kimi Code through Kunavo against its own endpoint, so after the first request, check Usage to confirm the actual amount deducted.
Frequently asked questions
How much does the Kimi Code API cost?
The Kimi Code CLI itself is free MIT software (MoonshotAI/kimi-code, version 2.1.1 dated September 24, 2026). What you pay for is model usage, which is sold in three ways. First, a Kimi membership at Plus or higher includes Kimi Code. As of October 1, 2026, kimi.com listed Plus at $19 per month ($15 per month with annual billing, $180 per year), Pro at $39 ($31, $372), Max at $99 ($79, $948), and Ultra at $199 ($159, $1,908). Second, Extra Usage is a wallet in yuan that takes over when the membership quota runs out. Third, you can skip the membership and pay per token on the Kimi Open Platform, where kimi-k3 costs $3 per million input tokens and $15 per million output tokens.
Which plan do I need to use Kimi Code and K3?
Plus is the starting point. Kimi's membership documentation says Kimi Code and K3 are available on Plus and above, while K3's 1M-token context and HighSpeed require Pro or higher. The Go plan has no coding quota. Higher-tier plans increase the agent quota on kimi.com (the pricing page shows 2x for Pro, 5x for Max, and 10x for Ultra compared with Plus), but no plan publishes a specific token or request count for Kimi Code.
What happens when Kimi Code quota runs out?
New subscribers have two limits. A rolling five-hour window limits bursts and recovers automatically. The weekly limit has been removed for new subscribers, while legacy plans still reset every seven days. The other limit is a total monthly quota shared with Kimi on the web; once it runs out, Kimi Code stops until reset or upgrade. After that, Extra Usage continues requests from a prepaid yuan balance, at rates Kimi says are close to Open Platform API prices. With Extra Usage enabled and no monthly spending limit set, there is no cap.
Is a Kimi membership cheaper than the Kimi API?
For heavy use, probably. Kimi's documentation itself says that upgrading the subscription usually offers better value than using a lot of Extra Usage. The break-even point depends on usage. At the kimi-k3 Open Platform rate, a session with 200,000 uncached input tokens and 12,000 output tokens costs about $0.78, so $19 for Plus equals about 24 such sessions a month; with kimi-k2.7-code, about 80. Kimi does not publish how many sessions Plus actually allows, so the honest test is to try the plan if your monthly metered API costs would exceed its price, and track usage in the Kimi Code Console.
Can I use another API, or a cheaper API, with Kimi Code?
Yes. The Kimi Code provider documentation describes an openai provider type for any OpenAI-compatible service by changing base_url, configured in ~/.kimi-code/config.toml. The /login selector offers only Kimi Code OAuth or a Kimi Platform API key, so other providers require editing the file. Membership and Open Platform use different model IDs and endpoints, so a configuration for one does not work for the other. Kunavo does not sell Kimi models; its Kimi Code setup page points the openai type to Claude and GPT IDs.
Read on October 1, 2026: kimi.com/membership/pricing (rendered in the browser), Kimi Code membership documentation, the chat pricing and quickstart pages on platform.kimi.ai, and the GitHub API for MoonshotAI/kimi-code. No Kimi account was used, and nothing was purchased or run. All amounts are calculations based on published rates; membership quotas are unpublished, so no per-token plan price is given.