LLM Reference
Moonshot AI Kimi

Using Kimi K3 on Moonshot AI Kimi

Implementation guide · Kimi · Moonshot AI

ServerlessOpen Weights

Moonshot AI Kimi exposes Kimi K3 through model ID kimi-k3. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-08-24. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Moonshot AI Kimi and generate an API key.
  2. 2
    Use the Moonshot AI Kimi SDK or REST API to call kimi-k3 — see the documentation for request format.
  3. 3
    You'll be billed $3.00/1M input, $15.00/1M output tokens. See full pricing.

Code Examples

See Moonshot AI Kimi documentation for integration details.

Pricing on Moonshot AI Kimi

TypePrice (per 1M)
Input tokens$3.00
Output tokens$15.00
Image input$1.00
Video input$1.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt Caching

About Kimi K3

Kimi K3 is Moonshot AI's 2.8-trillion-parameter flagship multimodal model for long-horizon coding, knowledge work, deep reasoning, and agentic workflows. It uses Kimi Delta Attention, Attention Residuals, and a sparse MoE design (16 of 896 experts active), supports a 1,048,576-token context window, text/image/video input, always-on reasoning, ToolCalls, strict JSON Schema structured output, automatic context caching, and partial mode through Moonshot's OpenAI-compatible API.

Model Specs

Released2026-07-14
Parameters2.8T total; 16 of 896 experts active
Context1.05m
ArchitectureMixture of Experts

Provider

Moonshot AI Kimi
Moonshot AI Kimi

Moonshot AI

New York City, New York, United States