Kimi K2.7

Moonshot's flagship multi-modal reasoning model — 256K context, image + VIDEO input, returns reasoning_content. Served via the OpenRouter credit pool (slug moonshotai/kimi-k2.7-code), failing over to direct Moonshot.

Code Examples

from blockrun_llm import LLMClient

client = LLMClient()  # Uses BLOCKRUN_WALLET_KEY (never sent to server)
response = client.chat("moonshot/kimi-k2.7", "Hello!")

Pricing

Payment