Model · MoonshotAI

Kimi K3 Fast

moonshotai/kimi-k3-fast

Try in Agents

Fast version of MoonshotAI's flagship K3 model for long-horizon coding and end-to-end knowledge work

reasoningvisioncaching

Specs

Context

Max output

131K

Provider

MoonshotAI

Input

$4.50/ 1M tokens

Output

$22.50/ 1M tokens

Cache read

$0.450/ 1M tokens

Providers and pricing

Vercel AI Gateway	List price	Our price
Input	$4.50 / 1M tokens	$4.50 / 1M tokens
Output	$22.50 / 1M tokens	$22.50 / 1M tokens
Cache read	$0.450 / 1M tokens	$0.450 / 1M tokens

List price is what the provider charges us. Our price is what a request is billed.

Live performance

Loading measurements…

How we measure. Every request is timed from the moment we send it. A finish time comes from the provider's own timestamps when it reports them, from the moment it calls us back when it doesn't, and otherwise from polling: we take the midpoint between the last check that found the job running and the first that found it done, so it is off by at most half the poll interval. First token is the wait for the first streamed text or tool token; output speed counts tokens after that first token. Requests you stop are left out. Figures appear once a window has 20 completed requests, and are aggregate only.

Try it

Chat with Kimi K3 FastTerramind API

⌘+Enter to run

Code

import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("kimi-k3-fast"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by MoonshotAI

Model	Context	In	Out	Capabilities
moonshotai/kimi-k2.6	262K	$0.950	$4.00	reasoningvisioncaching
moonshotai/kimi-k3	1M	$3.00	$15.00	reasoningvisioncaching