Kimi K2 Instruct

moonshotai/kimi-k2

A chat model with a 131K-token context window, at $0.5985 per million input tokens and $2.415 per million output tokens.

Details

Maker: moonshotai
Kind: Chat
Context window: 131,072 tokens
Max output: 131,072 tokens
Input: $0.5985 per million tokens
Output: $2.415 per million tokens
Capabilities: Tool use
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2025-07-11

Description

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.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model