Vision Languagetextimagevideo
Kimi K3
Kimi K3 is an open-weight, native multimodal model developed by Moonshot AI. It has 2.8 trillion total parameters and is built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a context window of up to 1 million tokens. It is designed for long-horizon coding, knowledge work, and reasoning.
Input
Reasoning
Max completion tokens
11048576
Ready to generateAPI Reference
POSThttps://api.token360.ai/v1/chat/completionscurl https://api.token360.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-api-key" \
-d '{
"model": "kimi-k3",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"temperature": 1,
"top_p": 0.95,
"max_completion_tokens": 4096
}'