Kimi Latest

Provider: moonshot · moonshot/kimi-latest

Pricing per million tokens

Component USD per 1M tokens
Input $2.00
Output $5.00
Cached input (read) $0.15

💡 With prompt caching, you save up to 93% on cached input tokens — massive for repeated context like system prompts, RAG retrieval, or long conversations.

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$2.45
per month
Saves $0.55 via caching
Medium
10M in / 2000k out
$24.45
per month
Saves $5.55 via caching
Large
100M in / 20000k out
$245
per month
Saves $55.50 via caching

Context

Input window
131,072 tokens
Max output
131,072 tokens

Capabilities

  • ✅ Vision (image input)
  • ✅ Function / tool calling
  • ⬜ Prompt caching
  • ⬜ Web search
  • ⬜ JSON / response schema

Compare Kimi Latest with similar models

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.