Kimi K3 API access to Moonshot AI's Kimi model family — K3 and K2.7 Code with strong reasoning, coding capabilities, and extended thinking modes.
Guides, comparisons and pricing analysis from the APIMart blog.
What's on your mind?
Ask APIMart
kimi-k3
Transparent pricing with no hidden fees. Pay only for what you use.
Per 1M tokens
| Rate | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|
| Input | 24~$2.4 | 22.8~$2.28 | 21.6~$2.16 | 30~$3 | 20% |
| Cached input | 2.4~$0.24 | 2.28~$0.228 | 2.16~$0.216 | 3~$0.3 | 20% |
| Output | 120~$12 | 114~$11.4 | 108~$10.8 | 150~$15 | 20% |
Access Kimi K3, K2.7 Code, K2-Thinking, and K2.6. Moonshot AI's frontier models delivering strong reasoning, coding, and extended thinking capabilities.
50K+
Active Users
99.9%
Uptime
2x
Faster
70%
Cost Savings
Why Kimi models are gaining traction among AI developers
How teams use Kimi models in production
Start using Moonshot's models in minutes
Create your free APIMart account and top up your balance.
Generate an API key to access Kimi models programmatically.
Use the playground above or integrate via the OpenAI-compatible API.
What developers say about our Kimi API
“Kimi K2's coding ability is seriously impressive. It handles complex refactoring tasks with ease.”
Alex Chen
Senior Developer
“K2-Thinking solved math problems that GPT-4o couldn't. The reasoning depth is remarkable.”
Sarah Li
AI Researcher
“K2.5 is a big step up. We've integrated it into our content pipeline for Chinese and English.”
Mike Wang
Content Lead
“Competitive pricing and solid performance. Kimi is an excellent alternative to the big providers.”
Emily Zhou
Product Manager
“The thinking mode is perfect for our legal analysis tool. It works through complex cases methodically.”
David Liu
Legal Tech Engineer
“Fast API, clean documentation, and reliable uptime. Very happy with the switch to APIMart for Kimi.”
Lisa Zhang
Backend Developer
Common questions about using the Kimi API
We offer the latest Kimi K3, plus K2.7 Code, K2.7 Code Highspeed, K2.6, and K2.5. Earlier K2 Instruct and K2 Thinking remain available.
K3 is the latest Kimi model from Moonshot AI, with a context window of up to 1M tokens. K2.7 Code is built for programming, and K2-Thinking adds extended reasoning for complex problems.
Kimi K3 (sometimes searched as Kimi3) is Moonshot AI's latest model, with a context window of up to 1M tokens, and is the pick for the newest capabilities and long context. K2.6 and K2.5 remain available for existing workflows, K2.7 Code is built for programming, and K2-Thinking adds extended reasoning. They all share one APIMart API key, so switching only means changing the model ID.
Token-based pricing (input + output). Check the pricing table above for specific rates.
Yes. Kimi models use the standard chat completions format and work with the OpenAI SDK.
Yes. Your API data is not stored or used for training. All requests are encrypted.
K3 for the latest capabilities and long context. K2.7 Code for coding, or K2.7 Code Highspeed for faster coding responses. K2-Thinking for complex reasoning.
The Moonshot AI Kimi K3 API is billed per million input and output tokens. The pricing table on this page lists all available options. Prices shown are Gold member prices (20% off); Platinum and Diamond members save even more, up to 28%. You only pay for successful requests.
Sign up for APIMart, open the API Keys page in your dashboard and create a key. The same key works for the Moonshot AI Kimi API and every other model on the platform, with pay-as-you-go billing and no subscription.
No. There is no free quota for the Kimi K3 API. It is pay-as-you-go, you only pay for successful requests, and all prices are 20% off for members.
The Moonshot AI Kimi API is OpenAI-compatible: call APIMart's Chat Completions endpoint with the OpenAI SDK or any HTTP client, authenticate with your APIMart API key, and set model to the Kimi model you want from this page. Full parameters and code examples are in the APIMart docs (docs.apimart.ai).
You can reach us via the live chat in the bottom-right corner, email us at [email protected], or join our Discord community. Our team will get back to you as soon as possible.
Explore more models in the same category.
Gemini 3.5 Flash Lite
A lightweight multimodal model launched by Google that emphasizes low cost, low latency, and high throughput. It is suitable for document parsing, data extraction, structured output, and large-scale agent workflows, delivering faster response times while maintaining core reasoning capabilities.
Gemini 3.6 Flash
Gemini 3.6 Flash is a faster, more token-efficient, and more code-capable version of the Gemini Flash model, suitable for everyday development, AI agents, and high-concurrency applications.
Kimi K2.6
A general-purpose large language model launched by Moonshot AI, featuring strong reasoning, coding, and agent capabilities, making it suitable for handling complex tasks.
GLM 5.2
Zhipu AI has launched a new-generation large language model that enhances reasoning, coding, and agent capabilities, making it suitable for complex tasks, development, and enterprise applications.