← model directory

moonshotai

MoonshotAI: Kimi K3

moonshotai/kimi-k3

⚙ tool calling

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...

specs & pricing
Type
text
Provider
moonshotai
Model ID
moonshotai/kimi-k3
Capabilities
vision, tools, reasoning
Context window
1.0M tokens
Input price
$0.33 / 1M tokens
Output price
$13.13 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$13.46

$0.33 for a million input tokens plus $13.13 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

cloud only

MoonshotAI: Kimi K3 is a hosted model, so it is always served from the cloud. Route easy traffic to an open model on your own hardware and keep this one for the requests that need it.

/// initialize

Call MoonshotAI: Kimi K3 through one OpenAI-compatible endpoint.

Mix it with open models on your own hardware — the gateway routes each request to the cheapest place that can serve it.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of MoonshotAI: Kimi K3?
MoonshotAI: Kimi K3 accepts up to 1,048,576 tokens (1.0M) of context per request.
How much does MoonshotAI: Kimi K3 cost per million tokens?
Through Wide Area Intelligence, MoonshotAI: Kimi K3 costs $0.33 per 1M input tokens and $13.13 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $13.46.

More from moonshotai

← browse all models