Moonshot AI

Kimi K3

About

Kimi K3 is a 2.8T open-weight model from Moonshot AI. Moonshot Kimi K3. Text, multi-image, and native video. It accepts text, images, and video. Context window is 256K. Released June 13, 2026.

Parameters
2.8T
Published parameter count.
Context window
256K
Tokens of context on a request.
License
Kimi K3 License
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$3
Cached input / 1M	$0.30
Output / 1M	$15

Compare

Kimi K3 is one of the catalog's chat models. The table is each model's published price, size, and context.

Model	What it does	Price	Parameters	Context
Kimi K3	Moonshot Kimi K3. Text, multi-image, and native video.	$3 / 1M input	2.8T	256K
Qwen3.5 0.8B	Multimodal chat model with up to 64 images or one video per request.	$0.08 / 1M input	0.8B	256K
Gemini 3.5 Flash Lite	Fastest and cheapest Gemini tier. Multimodal chat; emits no reasoning tokens.	$0.30 / 1M input	—	1M
Gemini 3.7 Flash	Newest Gemini Flash tier with extended reasoning. Multimodal chat + native video.	$0.75 / 1M input	—	1M

Benchmarks

Published scores for Kimi K3, from the Kimi K3 model card. Vision scores without tools.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	MMMU-Pro: 81.6.
Cost and performance	Lower listed rate, mid-pack latency

Performance

Latency is the end-to-end round trip. Throughput is completion tokens divided by that time. It is a request rate, not decode speed.

Latency
—
Throughput
—
Requests
55

Methods

Methods this model serves. Payload shapes are in the docs.

Method	Returns
detection	Boxes around objects
chat	The model's reply

Estimate cost

Estimate. An hour of video is 15 frames a minute at 256 tokens a frame, plus the audio in that request, and 500 output tokens a minute.

Hours of video

$1,486.80

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k3",
    messages=[{"role": "user", "content": "What is in this image?"}],
)

print(response.choices[0].message.content)