Kimi K2 Instruct
Moonshot AI
Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.
- Language
- Tool use
- Context
- 131K
- Max output
- 131K
- Input / 1M
- $0.570
- Output / 1M
- $2.30
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass moonshotai/kimi-k2 as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$0.570
Output
Per 1M completion tokens
$2.30
A 1M-token prompt with 250K tokens of output costs about $1.15.