Skip to content

Latest commit

 

History

History
101 lines (66 loc) · 2.68 KB

File metadata and controls

101 lines (66 loc) · 2.68 KB

Kimi K3


Table of Contents


Quickstart

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokenfactory.nebius.com/v1/",
    api_key=os.environ.get("NEBIUS_API_KEY")
)

response = client.chat.completions.create(
    model="moonshotai/Kimi-K3",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}]
)
print(response.choices[0].message.content)

Try it Out

▶ Try it in the Token Factory Playground

sample code : kimi-k3-1.ipynb

Open In Colab

Run it locally as follows

# prepare .env file
cp  .env.example  .env
# Add your NEBIUS_API_KEY to .env

# run the notebook
uv run jupyter lab kimi-k3-1.ipynb

TL;DR

Kimi K3 is Moonshot AI's flagship reasoning model, released July 2026 — a major step up in intelligence over the Kimi K2.5 / K2.6 / K2.7 lineage, with multimodal (text + image) input and a 1M-token context window.

  • Provider: Moonshot AI (Kimi)
  • Architecture: Proprietary — 2.8T parameters
  • Context window: 1M tokens
  • Strengths: Reasoning, knowledge, mathematics, coding, agentic tasks, multimodal (image) understanding
  • License: Proprietary (Moonshot AI)

Key highlights

  • First Open weights model to approach 3 T parameter count.
  • Scores 57 on the Artificial Analysis Intelligence Index, ranking #7 of 190 models (category median: 32)
  • Multimodal input — supports text and image; outputs text

Examples and Resources

Apps and demos

Coding


Performance and Benchmarks


References