# MoonshotAI: Kimi K3

Provider: moonshotai  
Category: llm  
Model ID: `moonshotai/kimi-k3`

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

- Context length: 1048576 tokens
- Max output: 943718 tokens
- Modalities: text, image, video
- Released: 2026-07-16

## Pricing

- Input: $3.00 per million tokens
- Output: $15.00 per million tokens

## Verdict

Kimi K3 offers a massive 1M-token context window at $3 input / $15 output per Mtok — roughly half the cost of GPT-4o for long-context work. The model handles text and image inputs, making it viable for multimodal document analysis. Without public benchmarks, you're trading proven performance data for cost savings on context-heavy tasks. Reach for this when budget and context length matter more than established track record.

---
Last verified: 2026-09-04T02:00:56.012Z  
Canonical URL: https://switchy.build/directory/models/kimi-k3