Kimi K3 online, no download.

What Kimi K3 is

A 2.8 trillion parameter open-weight model from Moonshot AI, with a context window of one million tokens. It reasons before it answers, it reads images as well as text, and it calls tools natively. In our catalog it is the largest model we serve and the one with the highest price per token, which is the same sentence read twice.

Running it on your own hardware is not a question of buying a better graphics card. A model this size lives across a rack, so the realistic choice is not between local and hosted, it is between hosted and not using it. Our write-up of the K3 launch goes through what the numbers on the model card actually mean.

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, which is the fastest debugging loop the Studio has.
• Native tool calls, so Agent mode and the coding agent run on it directly with no prompt translation in between.
• A Think switch that saves money. 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 38 chat models on the same account, plus the image, video and audio studios. K3 is one pick in the list, not a separate product.

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",
       "messages":[{"role":"user","content":"Hello"}]}'

How to start in three steps

1. Buy a €5 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 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 is the priciest model in our catalog per token, so that token count above is the floor of what the pack buys, not an average of your week: input tokens draw from the same wallet, and a long conversation carries its whole history into every turn. Credits are one pool for text, images and video together, so a batch of renders and an agent session spend the same budget. Cloud runs on shared hardware, so at busy hours a request can wait a few seconds in a queue 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