Moonshot AIReasoning Model

Kimi K3 Fast

Kimi K3 on a low-latency serving tier: the same open-weight flagship — 1M-token context, native vision, configurable reasoning — traded at a higher per-token price for markedly faster generation. For interactive agents where response speed matters most.

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "kimi-k3-fast",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "kimi-k3-fast",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}

Related models

Model

InputCache readOutput

Kimi K3

1024K input contextVisionToolsReasoning$3.00 / $15.00

1000K input contextTools$2.50 / $5.00

$2.50

$5.00

Schematron V2 SmallInference.net

125K input context$0.05 / $0.25

$0.05

$0.25

Schematron V2 TurboInference.net

125K input context$0.03 / $0.15

$0.03

$0.15

Start building with Kimi K3 Fast today

Serverless, OpenAI-compatible, and billed per token. No commitments.