EasyAPI

kimi-k3

文本

A multimodal reasoning model for complex coding, knowledge work, and long-running agent tasks. It works across large codebases, calls tools, and debugs, using images, logs, and test output to refine its output.

Input price

¥15.787320% off

Market: ¥19.7341

/ M

Output price

¥78.936520% off

Market: ¥98.6706

/ M

Cache read

¥1.578720% off

Market: ¥1.9734

/ M

Input

Text

Output

Text

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

1

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token
shell
export EASYAPI_API_KEY=sk-xxxxxxxx
2

Make your first request

Use moonshot/kimi-k3 with the EasyAPI API:

cURL
curl https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{
  "model": "moonshot/kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'
3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

curl
curl -N https://token.easyapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"moonshot/kimi-k3","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

Endpoint

Sends a chat completion request. Supports streaming and non-streaming modes.

POSThttps://token.easyapi.com/v1/chat/completions
Authorization
Bearer $EASYAPI_API_KEY
Content-Type
application/json
Model
moonshot/kimi-k3

Send a chat completion request, with streaming or non-streaming responses. Docs

GEThttps://token.easyapi.com/v1/models
Authorization
Bearer $EASYAPI_API_KEY

List the models available to the current account. Docs

Parameters

NameTypeDefaultDescription
modelstring—Model ID, e.g. openai/gpt-4o or anthropic/claude-3-5-sonnet
messagesarray—List of conversation messages, each with role and content
streambooleanfalseWhen true, the response is streamed via SSE
temperaturefloat1Sampling temperature; higher values are more random
max_tokensinteger—Maximum number of tokens generated in a single reply
top_pfloat1Nucleus sampling; limits the cumulative probability of candidate tokens
frequency_penaltyfloat0Frequency penalty; reduces repeated wording
presence_penaltyfloat0Presence penalty; encourages new topics

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

kimi-k3 FAQ

How is the kimi-k3 API billed?
kimi-k3 is pay-as-you-go from ¥15.7873 / M. The exact rate is listed in the pricing table on this page and billed at EasyAPI's public price, with no subscription required.
How do I call kimi-k3 through the API?
EasyAPI exposes an OpenAI-compatible API: create an API key in the console, set base_url to https://token.easyapi.com and model to moonshot/kimi-k3, then send requests to /v1/chat/completions. The Quick Start on this page includes cURL, Python and TypeScript examples; official OpenAI SDKs only need the base_url swapped.
Which request formats does kimi-k3 support?
OpenAI Chat Completions format including streaming (stream). Official OpenAI and Anthropic SDKs work by swapping base_url; see the Parameters table on this page for the full list.
How do I get started with kimi-k3?
Sign up for EasyAPI, create an API key in the console and top up your balance to call kimi-k3 pay-as-you-go, no subscription needed. You can also try it in the online Playground first, then copy the Quick Start example.

Related models

All models

deepseek-v4-pro-0813

DeepSeek

DeepSeek V4 系列旗舰，深度推理与代码生成能力达系列高位，适合全代码库分析、多步骤自动化与高难度指令场景。

文本
55% off
Input price

¥1.984/ M

Output price

¥5.9519/ M

Cache read

¥0.0661/ M

Cache write

—

deepseek-v4.1-flash

DeepSeek

DeepSeek-V4.1-Flash 是 DeepSeek 当前主力模型，官方 API 模型名为 deepseek-flash。支持 1M 上下文与最大 384K 输出，默认可切换思考/非思考模式，具备图像理解、工具调用、JSON Output，并兼容 OpenAI 与 Anthropic API。

文本
58% off
Input price

¥0.4181/ M

Output price

¥1.6725/ M

Cache read

¥0.0084/ M

Cache write

—

doubao-seed-2.0-code-preview-260215

ByteDance

面向 Agent 工作流的代码预览模型，在 SWE-Bench、LiveCodeBench 上跑出接近一线的成绩，适合自主编码智能体与多语言工程任务。

文本
15% off
Input price

¥5.678/ M

Output price

¥34.068/ M

Cache read

¥0.5678/ M

Cache write

¥0.0473/ M

doubao-seed-2.0-lite

ByteDance

Seed 2.0 系列轻量档，延迟低、调用成本可控，智能体、编程与 GUI 任务表现稳定，适合高频交互场景与大批量任务分发。

文本
6% off
Input price

¥0.5565/ M

Output price

¥3.339/ M

Cache read

¥0.1113/ M

Cache write

—

Popular comparisons for kimi-k3