Conversation / Quote

Kimi-K3 API Price

Moonshot Kimi logo Moonshot Kimi · kimi-k3

Add to comparison

Input · Cache Miss
¥20 /1M tokens
Output
¥100 /1M tokens
Cache Hit Input
¥2 /1M tokens
BillingCNY · 1M tokens
Context Window1049K tokens
ModalitiesText / Image / Video
Deep ThinkingSupported
Verified Date2026-09-24
Official pricing pagewww.kimi.com/zh-hans/resources/kimi-k3-pricing ↗

Source text: the note below is the model's official text, kept in its original Chinese and not translated.

旗舰,1M 上下文(1,048,576 tokens);缓存写入 5min ¥20 / 1h ¥40(缓存写入字段取默认 5min 档);海外站 $3/$15。价格与缓存写入经官方文档 platform.kimi.com/docs/pricing/chat「K3 系列模型」表逐项核对(本条目 sourceUrl 的资源页为 JS 渲染,静态抓取不可得)

Report a pricing issue

Found inaccurate pricing or model information? We will review it.

Monthly Cost Estimate

30 days · no cache hits · list price

Light Load
1M Input + 0.3M Output/ day
¥1,500/month
Medium Business
5M Input + 1.5M Output/ day
¥7,500/month
Heavy Agent
10M Input + 3M Output/ day
¥15,000/month

Free quotas, tiered pricing, batch discounts, and time-based pricing are not included; refer to official bills.

Moonshot Kimi Related Models

FAQ

How much does the Kimi-K3 API cost?

Input ¥20/1M tokens, output ¥100/1M tokens

How large is the Kimi-K3 context window?

1049K tokens. Handles long documents, multi-turn conversations and large-scale inputs.

Does Kimi-K3 support prompt caching?

Yes. Cache writes cost ¥20/1M tokens and cache-hit reads cost ¥2/1M tokens. This significantly cuts the cost of repeated input — ideal for long system prompts and codebase analysis.

Which input modalities does Kimi-K3 support?

Text / Image / Video. Supports deep thinking / reasoning.

What is the approximate monthly cost of Kimi-K3?

Depends on volume: light use (1M input + 300K output per day) ≈ ¥1,500/month; medium (5M + 1.5M) ≈ ¥7,500/month; heavy agents (10M + 3M) ≈ ¥15,000/month. Cache hits, batch discounts and tiered pricing can lower this further.

How does Kimi-K3 compare with peers on value?

Moonshot Kimi Kimi-K3 is competitively priced among comparable models; compare against GPT-4o, Claude 3.5 and Gemini 2.5. See the Pricemon market table for a full comparison.

What use cases suit Kimi-K3?

Good for: chat systems, customer support, content generation, coding assistance, data analysis.The long context supports deep-analysis scenarios.

Does Kimi-K3 have a free tier?

Check Moonshot Kimi's official pricing page for the latest free quota, trial policy and tiered pricing. Policies differ by vendor and change over time.

← Back to Market