Kimi K3
Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, it offers native visual understanding and a 1M-token context window for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning.
byKimiInput TypetextimageOutput TypetextContext Window1MMax Output262K
Providers
This model is available from multiple providers. Select one to see its pricing and sample code.
KimiDefault
$2.1 / $10.5/ 1M tokens0.70× base price
Supported formatsOpenAI Chat CompletionsOpenAI ResponsesAnthropic Messages
Official Channels of Kimi
Pricing
Transparent pay-as-you-go pricing by token usage — no subscriptions or hidden fees.
Per 1M tokens
Input
Prompt and context tokens
$2.1
Output
Generated completion tokens
$10.5
Cache read
Reused or stored prompt context
$0.21
Code
Copy an example below to start calling this model in minutes.
API / request example
Sample Code & API
from openai import OpenAI
client = OpenAI(
base_url="https://api.apipod.ai/v1",
api_key="<YOUR_API_KEY>",
)
# Chat Completions
completion = client.chat.completions.create(
model="kimi-k3",
messages=[
{
"role": "user",
"content": "What is the meaning of life?",
}
],
)
print(completion.choices[0].message.content)