Moonshot AI
Open weights2 channelskimi-k3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at.
Aggregated modalities
Available from 2 channels
Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.
ChannelUSD per 1M tokensInputOutputCache readCache write
jd/kimi-k3Lowest input
Input
$2.8572 USD per 1M tokens
Output
$14.2858 USD per 1M tokens
Cache read
$0.2858 USD per 1M tokens
Cache write
- USD per 1M tokens
moonshotai/kimi-k3Input
$3.00 USD per 1M tokens
Output
$15.00 USD per 1M tokens
Cache read
$0.30 USD per 1M tokens
Cache write
$3.00 USD per 1M tokens
Endpoints
POST
/v1/chat/completionsChat CompletionsCall it
Using jd/kimi-k3
1from openai import OpenAI23client = OpenAI(4 base_url="https://www.realrelay.ai/v1",5 api_key="sk-***",6)78response = client.chat.completions.create(9 model="jd/kimi-k3",10 messages=[{"role": "user", "content": "Hello"}],11)1213print(response.choices[0].message.content)1import OpenAI from "openai";23const client = new OpenAI({4 baseURL: "https://www.realrelay.ai/v1",5 apiKey: process.env.REALRELAY_API_KEY,6});78const response = await client.chat.completions.create({9 model: "jd/kimi-k3",10 messages: [{ role: "user", content: "Hello" }],11});1213console.log(response.choices[0].message.content);1curl https://www.realrelay.ai/v1/chat/completions \2 -H "Authorization: Bearer $REALRELAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "jd/kimi-k3",6 "messages": [{ "role": "user", "content": "Hello" }]7 }'Prices and availability as published on Oct 4, 2026.
Capabilities
ReasoningStructured outputTool useVision
Input
TextImageVideo
Output
Text
