Kimi K3

Kimi K3 is Moonshot AI's flagship multimodal model for long-horizon coding, knowledge work, and reasoning, available through the Kimi API with a 1M-token context window.

Platform: Replicate

Language ModelMultimodalCoding AssistantAgent WorkflowsLong ContextMoonshot AI

0 runs

Kimi API / Kimi Code / Kimi Work

Kimi international API: $0.30 per million cache-hit input tokens, $3 per million cache-miss input tokens, and $15 per million output tokens

Commercial

🚀Function Overview

Kimi K3 is a 2. Ready to experience the power of AI? Start your journey here!

Key Features

Official Kimi API model ID kimi-k3
1-million-token context window
Native vision for text, image, and video-oriented workflows
2.8 trillion total parameters with 16 of 896 experts activated
Kimi Delta Attention and Attention Residuals architecture
Max thinking effort at launch, with low and high effort modes planned
Official international API pricing for cache-hit input, cache-miss input, and output tokens
Full model weights scheduled for release by July 27, 2026

Use Cases

•Long-horizon software engineering through Kimi Code or an API agent harness
•Repository and document analysis using a 1M-token context window
•Multimodal reasoning over text, images, screenshots, and video
•Knowledge-work agents for research, spreadsheets, presentations, and reports
•Frontier-model routing experiments that compare task success, price, and review burden

⚙️Input Parameters

model

string

Use kimi-k3 on the Kimi API or a provider surface that explicitly lists the model.

messages

array

OpenAI-compatible conversation payload for text, multimodal, coding, reasoning, and tool-use workflows.

tools

array

Optional tool definitions for coding agents and other tool-using workflows where the active API surface supports them.

temperature

number

Sampling temperature; Moonshot reports temperature 1.0 for its launch benchmark runs, but applications should follow current API guidance.

top_p

number

Nucleus sampling control; Moonshot reports top-p 1.0 for its launch benchmark runs.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Inspect this repository plan, identify the riskiest assumption, and propose the smallest verifiable implementation sequence."
    }
  ]
}

Output Results

Kimi K3 returns a structured coding or reasoning response through the Kimi API. Validate the exact response shape, effort controls, tool support, and account limits against the current API documentation before production use.

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: Kimi API / Kimi Code / Kimi Work
Run Count: 0
Commercial Use: Supported
Pricing: Kimi international API: $0.30 per million cache-hit input tokens, $3 per million cache-miss input tokens, and $15 per million output tokens
Platform: Replicate

Related Keywords

Kimi K3kimi-k3Moonshot AI Kimi K3Kimi K3 APIKimi K3 pricingKimi K3 context windowKimi K3 open weightsKimi K3 coding modelKimi K3 vision modelKimi Delta Attention

Related Models

Bielik 1.5B v3 Instruct

Bielik-1.5B-v3-Instruct is a generative text model featuring 1.6 billion parameters. It is result of collaboration between the open-science/open-souce project SpeakLeash and the High Performance Computing (HPC)

Cordia-A6 Text Generation Model

A model for generating text sequences based on input prompts and adjustable parameters.

Claude Sonnet 4

Claude Sonnet 4 is a significant upgrade to 3.7, delivering superior coding and reasoning while responding more precisely to your instructions