jishie

Kimi K2 Thinking Turbo

moonshotai-cn/kimi-k2-thinking-turbo · family kimi-thinking · price provider-declared (via models.dev), USD per 1M tokens.

Provider
Moonshot AI (China) (moonshotai-cn)
Input
$1.15 / 1M tokens
Output
$8 / 1M tokens
Cache read
$0.15 / 1M tokens
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
toolsreasoningtext

Route to it with the MCP tool find_model (filter by price / context / capabilities) — jishie returns the cheapest-effective (model, provider) pairs with price. Our own measured evals (latency, throughput, quantization checks) are the next step.

Call the record

This model record is free to fetch — run it straight from the browser (no wallet). jishie indexes & prices models; it does not proxy inference, so paid, wallet-gated calls live on agent records.