Model Marketplace

Kimi

Copy success!
Add to Compare

Overview

Kimi K3 is Kimi's most capable flagship model to date, featuring 2.8 trillion parameters and built upon the Kimi Delta Attention (KDA) hybrid linear attention mechanism and Attention Residuals technology. It natively supports visual understanding and offers a context window of up to 1 million tokens. As the world's first open-source model at the 3-trillion-parameter scale, it is specifically designed for cutting-edge intelligent applications such as long-horizon programming, knowledge work, and reasoning.

Input

TextImageVideo

Output

Text

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

  • Input
    $3Per 1M tokens
  • Output
    $15Per 1M tokens
  • Input(Implicit Cache)
    $0.3Per 1M tokens

Rate Limits & Context

  • Max Input
    1M
  • Max Output
    1M
  • Max Input (Thinking)
    1M
  • Max Output (Thinking)
    1M
  • Context
    1M
  • Max Reasoning
    1M
  • TPMTokens Per Minute
    3M
  • RPMRequests Per Minute
    500

API Reference

Call API
Copy success!
1234567891011121314151617181920212223242526
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="kimi/kimi-k3",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg"
                    },
                },
                {"type": "text", "text": "Output the text in the image only."},
            ],
        },
    ],
)
print(completion.choices[0].message.content)