Moonshot AI · Single modalityReleased 2025-09-05

kimi-k2

moonshotai/kimi-k2 id

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.

Tool use
Type
Use kimi-k2
# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$
$ const { text } = await generateText({
$ model: 'moonshotai/kimi-k2',
$ baseURL: 'https://synapse.garden/api/v1',
$ apiKey: process.env.MG_KEY,
$ prompt: 'Why is the sky blue?',
$ })
131.1K
CONTEXT WINDOW
131.1K
MAX OUTPUT
$0.627/M
INPUT · PER M
$2.53/M
OUTPUT · PER M
PRICING

List prices, every modality.

RatePer million tokens · USD
Input$0.627/M
Output$2.53/M
Honest list pricesHow we calculate prices
MORE FROM MOONSHOT AI

Other Moonshot AI models

See all 6
FAQ · KIMI-K2

Frequently asked

01 / 04

How do I call kimi-k2 from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘moonshotai/kimi-k2 and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does kimi-k2 cost?

Input: $0.627/M per million tokens. Output: $2.53/M per million tokens. The free tier includes a million tokens every month at no cost.

03 / 04

What's the context window for kimi-k2?

kimi-k2 supports a context window of 131.1K tokens, with a maximum output of 131.1K tokens.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try kimi-k2 in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.