Kimi K3.1 Pro online, no download.

What Kimi K3.1 Pro is

Moonshot AI released it on October 23, 2026. Underneath it is the Kimi K3 architecture, a mixture of experts with 2.8 trillion parameters of which about 104 billion work on each token, and a context window of one million tokens. The difference is the training after that: K3.1 Pro is tuned for long coding sessions and agents that work through many steps. It reasons before it answers, reads images as well as text, and calls tools natively.

Moonshot has announced open weights for it and named early November for them. Until they are published, and realistically after that too, the way to use it is hosted: a model this size lives across a rack of data-center GPUs, not in a desktop. If you want the background, our Kimi K3 page covers the base model.

What you get

• Chat in the browser, with no install, no driver and no VRAM check. Open the Studio, pick the model, type.
• Image input. Paste a screenshot into the composer and ask about it, up to ten images in one message.
• Native tool calls, so Agent mode and the coding agent run on it directly with no prompt translation in between.
• A Think switch and three effort levels. The model reasons on its own, and turning that off on questions that do not need it is the largest lever you have on the bill.
• All 48 chat models on the same account, Kimi K3 included, plus the image, video and audio studios.

Call it from your own code

Create a key under Cloud API keys in account settings, point the base URL at https://lu-labs.ai/api/inference/v1 and send the catalog model id. Anything that speaks the OpenAI chat completions format works, including Aider, LibreChat and a plain curl call. The key spends your credits and cannot read or change your account.

curl https://lu-labs.ai/api/inference/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/Kimi-K3.1-Pro",
       "messages":[{"role":"user","content":"Hello"}]}'

How to start in three steps

1. Buy a €15 credit pack, or take the Hosted plan if you want a monthly budget. Card details go to Stripe and the payment is secured with 3D Secure.
2. The Studio opens on your account. Pick Kimi K3.1 Pro in the model picker.
3. Type, or paste a screenshot. For scripts, create an API key in account settings and use the base URL above.

What it costs

The honest limits

Kimi K3.1 Pro is the priciest model in our catalog per token, so it moves a credit balance faster than anything else on the list. The input side draws on the same wallet as the answer, and a long conversation carries its whole history into every turn; repeated parts of a prompt are billed at a fraction of the input price. Credits are one pool for text, images and video together. Images have to be at least 64 by 64 pixels. Cloud runs on shared hardware, so at busy hours a request can wait a few seconds before it starts streaming. The catalog is curated: we host open-weight models we have priced and tested, and you cannot upload your own base model. Account data is hosted in the EU and you can delete it yourself. We never train on your data and we never sell it.

Questions