All AI models · LLM benchmarks · Methodology

Kimi K2 Turbo Preview

Fast Kimi model for responsive chat, coding help, and agent loops

Model facts

Context window
256K tokens
Maximum output
8K tokens
Cheapest paid input
$0.15 per 1M tokens
Cheapest paid output
$8 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

tool calling, temperature control, text.

Observed price history

  • 2026-08-24: $0.15 input / $8 output per 1M tokens

API providers