Blog · Kimi

Kimi API Pricing (2026): Cost, Context & Setup Guide

Kimi (Moonshot) is the go-to Chinese LLM for long documents and CJK-heavy workloads. This guide covers pricing, context lengths, and how to access it from outside China.

Last updated: 2026-10-08. All prices below are captured as of the dates noted — vendor pricing changes often, always verify on the official pricing page before buying.

1. What is Kimi?

Kimi is developed by Moonshot AI, a Beijing-based startup. Its standout feature is long-context support — the current Kimi K3 model handles up to 1M tokens, making it one of the few models that can ingest an entire codebase or multi-hundred-page document in a single pass.

Kimi is a strong fit for:

Long-document analysis — contracts, research papers, legal briefs, financial reports
Chinese-language workloads — CJK text processing where native tokenization matters
Codebase ingestion — feed an entire repository to a single context window
Agent memory — maintain long conversation histories without truncation

Unlike DeepSeek, Kimi does not use peak/off-peak pricing. Its official pricing tiers are based on context length rather than call time.

2. Official Kimi pricing (Moonshot first-party)

Moonshot publishes pricing on the official platform (kimi.moonshot.cn). The following rates were captured from the official documentation (verified 2026-09-10):

Model	Context	Input / 1M tokens	Output / 1M tokens
`kimi-k3-flash`	128K	¥0.60 (≈ $0.08)	¥2.00 (≈ $0.28)
`kimi-k3-pro`	128K	¥4.00 (≈ $0.56)	¥12.00 (≈ $1.67)
`kimi-k3-pro-1m`	1M	¥8.00 (≈ $1.11)	¥24.00 (≈ $3.34)

Official source: kimi.moonshot.cn (in CNY). USD approximations use 2026-09-10 exchange rate ~7.18 CNY/USD.

Key differences from other Chinese LLM providers:

Context-length tiering — Kimi charges more for 1M-context access than 128K. If you only need short contexts, the 128K tier is significantly cheaper.
No peak/off-peak pricing — the price is the same regardless of when you call.
Chinese credentials required — registration needs a Chinese phone number, and payment is CNY-only (Alipay, WeChat Pay, China-issued UnionPay). No PayPal, no international cards.

⚠️ Clarification: This article is written by AI24X, an AI gateway / API aggregator — we are not the official Moonshot AI service and we are not affiliated with Moonshot. We explain the official pricing for context and offer our own access as one of several alternatives.

3. Kimi vs DeepSeek — when context length matters

Kimi's main differentiator is context length. Here is how it stacks up against DeepSeek Flash on the official platforms (captured 2026-09-10):

Model	Context	Output / 1M (cheapest tier)	Best for
Kimi K3 Flash	128K	¥2.00 ($0.28)	Standard-length documents, CJK text
Kimi K3 Pro 1M	1M	¥24.00 ($3.34)	Whole-codebase analysis, massive docs
DeepSeek V4.1 Flash (off-peak)	1M	$0.60	General reasoning, coding, cost-sensitive
DeepSeek V4.1 Flash (peak)	1M	$1.20	—

DeepSeek Flash is cheaper for short-context work and has stronger reasoning. Kimi pulls ahead when you need to process very long inputs — its 1M-context Pro tier is designed for exactly that use case, while DeepSeek's 1M context is a general capability available on all tiers.

Through AI24X, both are available under one key. AI24X flash starts at $0.35/M output (verified 2026-10-02) and covers Kimi, DeepSeek, Qwen, GLM, MiniMax, and MiMo — the gateway routes each request to the best channel, so you do not need to maintain separate accounts for short-context and long-context workloads.

4. Accessing Kimi from outside China

If you are outside China and do not have a Chinese phone number, the first-party Moonshot platform is not an option. Two practical paths exist:

Path A: AI gateway (recommended for international developers)

AI gateways like AI24X provide Kimi access through an OpenAI-compatible endpoint. No Chinese phone number needed — signup uses email, payment uses PayPal or international card. Through AI24X, Kimi is available under the vip-kimi model ID on a flat rate with no context-length tiering.

Path B: Direct Moonshot platform (requires Chinese credentials)

If you have a Chinese phone number and payment method, register at kimi.moonshot.cn. The API endpoint is OpenAI-compatible (https://api.moonshot.cn/v1), which is rarer among Chinese providers — most use custom auth schemes. Moonshot uses standard Bearer token authentication.

5. One key for Kimi + DeepSeek + Qwen + GLM

Why use an aggregator instead of managing separate accounts:

One OpenAI-compatible endpoint: POST /v1/chat/completions with Authorization: Bearer <key>
One payment rail: PayPal or card — no Chinese phone number required
All Chinese model families on one key: Kimi, DeepSeek, Qwen, GLM, MiniMax, MiMo — plus GPT-5/Claude/Gemini when needed
Flat-rate billing: no context-length tiering, no peak/off-peak tracking, no per-model minimums
Smart routing: the gateway picks the best upstream channel per request, with automatic model switching

6. Worked cost example

Say a developer processes 30M input tokens and 6M output tokens per month, with half of the input going to long-context (1M) calls:

Scenario	Input bill	Output bill	Total
Kimi K3 Flash official (128K, all short)	30 × ¥0.60 = ¥18.00	6 × ¥2.00 = ¥12.00	¥30.00 (~$4.18)
Kimi K3 Pro 1M official (mixed context)	30 × ¥8.00 = ¥240.00	6 × ¥24.00 = ¥144.00	¥384.00 (~$53.48)
DeepSeek V4.1 Flash official (all off-peak)	30 × $0.15 = $4.50	6 × $0.60 = $3.60	$8.10
AI24X flash tier (flat, multi-model)	— (flat output pricing)	~6 × $0.35 = $2.10	varies by routing — effective bill typically below official peak rates

The takeaway: if your workload is mostly short-context, DeepSeek Flash is cheaper per token. If you regularly need 1M-context passes, Kimi K3 Pro 1M is purpose-built for that — but at a premium. An aggregator with flat-rate pricing simplifies the decision: you pay one rate and the gateway routes to the best model for each request.

7. Copy-paste setup

Base URL (OpenAI-compatible)

https://api.ai24x.com/v1

Quick test with curl

curl -X POST "https://api.ai24x.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ***" \
  -d '{"model":"vip-kimi","messages":[{"role":"user","content":"Summarize this document in 3 bullet points."}]}'

Python with OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ai24x.com/v1",
    api_key="***"
)

response = client.chat.completions.create(
    model="vip-kimi",
    messages=[{"role": "user", "content": "Analyze this 200-page contract."}]
)
print(response.choices[0].message.content)

Existing OpenAI SDKs and tools (Open WebUI, LobeChat, Cursor, Dify, LiteLLM, n8n) connect the same way: change base URL + key, keep the rest of your code.

8. FAQ

Is Kimi API free?

Moonshot offers a limited free tier on the official platform. Through AI24X, a shared free channel of 100K tokens/day is available when your balance is empty — see the console for current policy.

Can I use the Kimi API without a Chinese phone number?

Not on Moonshot's first-party platform. Through AI24X, yes — signup requires only an email, and payment is by PayPal or international card.

Does Kimi have peak/off-peak pricing?

No. Moonshot charges a flat rate regardless of call time. AI24X also bills flat with no surcharge.

Is AI24X the official Kimi API?

No. AI24X is an independent AI gateway (not affiliated with Moonshot AI) that routes to Kimi and other models through one OpenAI-compatible key.

What context length should I use?

For most tasks, the 128K tier is sufficient. Use the 1M tier only when you genuinely need to pass entire codebases, long books, or multi-hundred-page documents in a single context window.

What is the refund policy?

Refund rules are set per platform. AI24X's billing is prepaid-credit based; check the console's billing/refund terms for the current policy, and top up only what you plan to use.

9. Getting started

Register at https://www.ai24x.com and create an API key in the console.
Top up at console → billing (PayPal or card).
Use the base_url + key from the setup section in any OpenAI-compatible tool — done.

Developer docs: https://open.ai24x.com · Console: https://www.ai24x.com/console.html · Pricing: https://www.ai24x.com/pricing.html · Model page: Kimi on AI24X

Educational/informational article. This page is not affiliated with Moonshot AI and does not constitute investment advice of any kind. All prices are as captured on the dates noted and may change; always check official pricing pages.

One API. Every AI. Pay Less.

Start Building Free Get API Key View pricing