Product
Kimi K3: specs, API pricing and data
Updated
Moonshot AIAI Models & LLMs
- Context window
- 1,048,576 tokens
- Open weights (downloadable)
- Yes
Data sheet · Kimi K3
Every figure is quoted from the vendor's official page, with the date we read it. If a row is missing, the source does not state it and we do not estimate it.
Memory and answer length
- Context window
- 1,048,576 tokensRank 5 of 21
What it means and the source
How much text the model keeps in view in a single request, question and answer included. It matters for long documents and whole code projects. A token is a fragment of a word.
huggingface.coOpens the source in a new tab Oct 23, 2026
Knowledge and abilities
- Reads images
- Yes13 models out of 23
What it means and the source
The model can take images (photos, screenshots, charts) as well as text.
huggingface.coOpens the source in a new tab Oct 23, 2026
Size and openness
- Parameters
- 2.8 trillion
What it means and the source
The size of the network: how many billions of learned values make it up. Bigger does not necessarily mean better, but it tells how much hardware it takes to run it yourself.
huggingface.coOpens the source in a new tab Oct 23, 2026- Active parameters per token
- 104 billion
What it means and the source
In «mixture of experts» models only part of the network works on each word: these are the parameters actually used for each token, and they matter for speed and running costs.
huggingface.coOpens the source in a new tab Oct 23, 2026- Open weights (downloadable)
- Yes7 models out of 23
What it means and the source
The model's weights can be downloaded: you can run it on your own servers, adapt it and decide where the data stays, within the licence terms.
huggingface.coOpens the source in a new tab Oct 23, 2026
Hardware to try AI at home
Kimi K3: just holding the weights in memory takes about 5,600 GB at 16-bit, 2,800 GB at 8-bit, 1,400 GB at 4-bit. Beyond 24 GB it is not a home-PC job: using it through an API makes more sense.Worked out from the billions of parameters the vendor states, not a measurement: context and the runtime need more memory.
Questions and answers
Kimi K3: how much text can it read at once?
The context window is 1,048,576 tokens.
Kimi K3: can I run it on my own computer?
Yes, the vendor publishes the model's weights. Parameters: 2.8 trillion. Holding them in memory takes about 1,400 GB at 4-bit; context and the runtime need more memory.
The short version
On Moonshot AI Kimi K3 the figure that actually matters is Context window: 1048576. I took that figure from Moonshot AI – model card (Hugging Face). Among the 21 I checked, 4 do better. The other figure to look at is Active parameters per token (billions): 104B.
The numbers on Moonshot AI Kimi K3
I put them in order of importance, with the value and the standing against the others I checked.
Context window: 1048576. Rank 5 of the 21 I compared.
Active parameters per token (billions): 104B. That is the best value among the 2 I compared.
Open weights (downloadable): 1. That is the best value among the 7 I compared.
Parameters (billions): 2.8T. That is the best value among the 7 I compared.
Reads images: 1. That is the best value among the 13 I compared.
Who it is for
Take it if Active parameters per token (billions) is your priority: 104B, and none of the ones I checked does better.
It suits you if you are after Open weights (downloadable): 1.
Look elsewhere if what matters to you is Context window: here it is 1048576, and 4 products do better.
Explore related coverage
Sources
Ask Sir Compare:Explain these numbers to me
Reviews and tests
Moonshot AI Kimi K3
Reviews and tests · Moonshot AI Kimi K3
Reviews are not available yet.
What changed
- Page updated
- Page updated